Upload folder using huggingface_hub
Browse files- .summary/0/events.out.tfevents.1725186806.a2f4d27d95e5 +3 -0
- README.md +1 -1
- checkpoint_p0/checkpoint_000002934_12017664.pth +3 -0
- replay.mp4 +2 -2
- sf_log.txt +538 -0
.summary/0/events.out.tfevents.1725186806.a2f4d27d95e5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c0f81be4ddd2400cffb66fb0a147f2285b94ec9b33fee60d624bdb36284c415
|
3 |
+
size 2545
|
README.md
CHANGED
@@ -15,7 +15,7 @@ model-index:
|
|
15 |
type: doom_health_gathering_supreme
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
-
value:
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
|
|
15 |
type: doom_health_gathering_supreme
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
+
value: 10.53 +/- 6.29
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
checkpoint_p0/checkpoint_000002934_12017664.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8cad2e39da2f0347adb76d84e96eed33c61a2e07913f2a183e7ed7a54495595
|
3 |
+
size 34928851
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c901054044bceb1335263c6b8dbf95c410bbb3d6e5df817c7551cfe66aa18399
|
3 |
+
size 20128244
|
sf_log.txt
CHANGED
@@ -7743,3 +7743,541 @@ main_loop: 11833.6824
|
|
7743 |
[2024-09-01 10:31:45,088][00307] Avg episode rewards: #0: 34.183, true rewards: #0: 13.583
|
7744 |
[2024-09-01 10:31:45,091][00307] Avg episode reward: 34.183, avg true_objective: 13.583
|
7745 |
[2024-09-01 10:33:19,526][00307] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7743 |
[2024-09-01 10:31:45,088][00307] Avg episode rewards: #0: 34.183, true rewards: #0: 13.583
|
7744 |
[2024-09-01 10:31:45,091][00307] Avg episode reward: 34.183, avg true_objective: 13.583
|
7745 |
[2024-09-01 10:33:19,526][00307] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|
7746 |
+
[2024-09-01 10:33:24,356][00307] The model has been pushed to https://huggingface.co/jarski/rl_course_vizdoom_health_gathering_supreme
|
7747 |
+
[2024-09-01 10:33:26,056][00307] Environment doom_basic already registered, overwriting...
|
7748 |
+
[2024-09-01 10:33:26,058][00307] Environment doom_two_colors_easy already registered, overwriting...
|
7749 |
+
[2024-09-01 10:33:26,061][00307] Environment doom_two_colors_hard already registered, overwriting...
|
7750 |
+
[2024-09-01 10:33:26,066][00307] Environment doom_dm already registered, overwriting...
|
7751 |
+
[2024-09-01 10:33:26,069][00307] Environment doom_dwango5 already registered, overwriting...
|
7752 |
+
[2024-09-01 10:33:26,074][00307] Environment doom_my_way_home_flat_actions already registered, overwriting...
|
7753 |
+
[2024-09-01 10:33:26,075][00307] Environment doom_defend_the_center_flat_actions already registered, overwriting...
|
7754 |
+
[2024-09-01 10:33:26,078][00307] Environment doom_my_way_home already registered, overwriting...
|
7755 |
+
[2024-09-01 10:33:26,079][00307] Environment doom_deadly_corridor already registered, overwriting...
|
7756 |
+
[2024-09-01 10:33:26,083][00307] Environment doom_defend_the_center already registered, overwriting...
|
7757 |
+
[2024-09-01 10:33:26,084][00307] Environment doom_defend_the_line already registered, overwriting...
|
7758 |
+
[2024-09-01 10:33:26,086][00307] Environment doom_health_gathering already registered, overwriting...
|
7759 |
+
[2024-09-01 10:33:26,087][00307] Environment doom_health_gathering_supreme already registered, overwriting...
|
7760 |
+
[2024-09-01 10:33:26,088][00307] Environment doom_battle already registered, overwriting...
|
7761 |
+
[2024-09-01 10:33:26,091][00307] Environment doom_battle2 already registered, overwriting...
|
7762 |
+
[2024-09-01 10:33:26,092][00307] Environment doom_duel_bots already registered, overwriting...
|
7763 |
+
[2024-09-01 10:33:26,095][00307] Environment doom_deathmatch_bots already registered, overwriting...
|
7764 |
+
[2024-09-01 10:33:26,096][00307] Environment doom_duel already registered, overwriting...
|
7765 |
+
[2024-09-01 10:33:26,097][00307] Environment doom_deathmatch_full already registered, overwriting...
|
7766 |
+
[2024-09-01 10:33:26,101][00307] Environment doom_benchmark already registered, overwriting...
|
7767 |
+
[2024-09-01 10:33:26,103][00307] register_encoder_factory: <function make_vizdoom_encoder at 0x789ab41c1b40>
|
7768 |
+
[2024-09-01 10:33:26,141][00307] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
7769 |
+
[2024-09-01 10:33:26,154][00307] Experiment dir /content/train_dir/default_experiment already exists!
|
7770 |
+
[2024-09-01 10:33:26,156][00307] Resuming existing experiment from /content/train_dir/default_experiment...
|
7771 |
+
[2024-09-01 10:33:26,159][00307] Weights and Biases integration disabled
|
7772 |
+
[2024-09-01 10:33:26,170][00307] Environment var CUDA_VISIBLE_DEVICES is
|
7773 |
+
|
7774 |
+
[2024-09-01 10:33:31,713][00307] Starting experiment with the following configuration:
|
7775 |
+
help=False
|
7776 |
+
algo=APPO
|
7777 |
+
env=doom_health_gathering_supreme
|
7778 |
+
experiment=default_experiment
|
7779 |
+
train_dir=/content/train_dir
|
7780 |
+
restart_behavior=resume
|
7781 |
+
device=cpu
|
7782 |
+
seed=None
|
7783 |
+
num_policies=1
|
7784 |
+
async_rl=True
|
7785 |
+
serial_mode=False
|
7786 |
+
batched_sampling=False
|
7787 |
+
num_batches_to_accumulate=2
|
7788 |
+
worker_num_splits=2
|
7789 |
+
policy_workers_per_policy=1
|
7790 |
+
max_policy_lag=1000
|
7791 |
+
num_workers=8
|
7792 |
+
num_envs_per_worker=4
|
7793 |
+
batch_size=1024
|
7794 |
+
num_batches_per_epoch=1
|
7795 |
+
num_epochs=1
|
7796 |
+
rollout=32
|
7797 |
+
recurrence=32
|
7798 |
+
shuffle_minibatches=False
|
7799 |
+
gamma=0.99
|
7800 |
+
reward_scale=1.0
|
7801 |
+
reward_clip=1000.0
|
7802 |
+
value_bootstrap=False
|
7803 |
+
normalize_returns=True
|
7804 |
+
exploration_loss_coeff=0.001
|
7805 |
+
value_loss_coeff=0.5
|
7806 |
+
kl_loss_coeff=0.0
|
7807 |
+
exploration_loss=symmetric_kl
|
7808 |
+
gae_lambda=0.95
|
7809 |
+
ppo_clip_ratio=0.1
|
7810 |
+
ppo_clip_value=0.2
|
7811 |
+
with_vtrace=False
|
7812 |
+
vtrace_rho=1.0
|
7813 |
+
vtrace_c=1.0
|
7814 |
+
optimizer=adam
|
7815 |
+
adam_eps=1e-06
|
7816 |
+
adam_beta1=0.9
|
7817 |
+
adam_beta2=0.999
|
7818 |
+
max_grad_norm=4.0
|
7819 |
+
learning_rate=0.0001
|
7820 |
+
lr_schedule=constant
|
7821 |
+
lr_schedule_kl_threshold=0.008
|
7822 |
+
lr_adaptive_min=1e-06
|
7823 |
+
lr_adaptive_max=0.01
|
7824 |
+
obs_subtract_mean=0.0
|
7825 |
+
obs_scale=255.0
|
7826 |
+
normalize_input=True
|
7827 |
+
normalize_input_keys=None
|
7828 |
+
decorrelate_experience_max_seconds=0
|
7829 |
+
decorrelate_envs_on_one_worker=True
|
7830 |
+
actor_worker_gpus=[]
|
7831 |
+
set_workers_cpu_affinity=True
|
7832 |
+
force_envs_single_thread=False
|
7833 |
+
default_niceness=0
|
7834 |
+
log_to_file=True
|
7835 |
+
experiment_summaries_interval=10
|
7836 |
+
flush_summaries_interval=30
|
7837 |
+
stats_avg=100
|
7838 |
+
summaries_use_frameskip=True
|
7839 |
+
heartbeat_interval=20
|
7840 |
+
heartbeat_reporting_interval=600
|
7841 |
+
train_for_env_steps=12000000
|
7842 |
+
train_for_seconds=10000000000
|
7843 |
+
save_every_sec=120
|
7844 |
+
keep_checkpoints=2
|
7845 |
+
load_checkpoint_kind=latest
|
7846 |
+
save_milestones_sec=-1
|
7847 |
+
save_best_every_sec=5
|
7848 |
+
save_best_metric=reward
|
7849 |
+
save_best_after=100000
|
7850 |
+
benchmark=False
|
7851 |
+
encoder_mlp_layers=[512, 512]
|
7852 |
+
encoder_conv_architecture=convnet_simple
|
7853 |
+
encoder_conv_mlp_layers=[512]
|
7854 |
+
use_rnn=True
|
7855 |
+
rnn_size=512
|
7856 |
+
rnn_type=gru
|
7857 |
+
rnn_num_layers=1
|
7858 |
+
decoder_mlp_layers=[]
|
7859 |
+
nonlinearity=elu
|
7860 |
+
policy_initialization=orthogonal
|
7861 |
+
policy_init_gain=1.0
|
7862 |
+
actor_critic_share_weights=True
|
7863 |
+
adaptive_stddev=True
|
7864 |
+
continuous_tanh_scale=0.0
|
7865 |
+
initial_stddev=1.0
|
7866 |
+
use_env_info_cache=False
|
7867 |
+
env_gpu_actions=False
|
7868 |
+
env_gpu_observations=True
|
7869 |
+
env_frameskip=4
|
7870 |
+
env_framestack=1
|
7871 |
+
pixel_format=CHW
|
7872 |
+
use_record_episode_statistics=False
|
7873 |
+
with_wandb=False
|
7874 |
+
wandb_user=None
|
7875 |
+
wandb_project=sample_factory
|
7876 |
+
wandb_group=None
|
7877 |
+
wandb_job_type=SF
|
7878 |
+
wandb_tags=[]
|
7879 |
+
with_pbt=False
|
7880 |
+
pbt_mix_policies_in_one_env=True
|
7881 |
+
pbt_period_env_steps=5000000
|
7882 |
+
pbt_start_mutation=20000000
|
7883 |
+
pbt_replace_fraction=0.3
|
7884 |
+
pbt_mutation_rate=0.15
|
7885 |
+
pbt_replace_reward_gap=0.1
|
7886 |
+
pbt_replace_reward_gap_absolute=1e-06
|
7887 |
+
pbt_optimize_gamma=False
|
7888 |
+
pbt_target_objective=true_objective
|
7889 |
+
pbt_perturb_min=1.1
|
7890 |
+
pbt_perturb_max=1.5
|
7891 |
+
num_agents=-1
|
7892 |
+
num_humans=0
|
7893 |
+
num_bots=-1
|
7894 |
+
start_bot_difficulty=None
|
7895 |
+
timelimit=None
|
7896 |
+
res_w=128
|
7897 |
+
res_h=72
|
7898 |
+
wide_aspect_ratio=False
|
7899 |
+
eval_env_frameskip=1
|
7900 |
+
fps=35
|
7901 |
+
command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
|
7902 |
+
cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
|
7903 |
+
git_hash=unknown
|
7904 |
+
git_repo_name=not a git repository
|
7905 |
+
[2024-09-01 10:33:31,723][00307] Saving configuration to /content/train_dir/default_experiment/config.json...
|
7906 |
+
[2024-09-01 10:33:31,729][00307] Rollout worker 0 uses device cpu
|
7907 |
+
[2024-09-01 10:33:31,731][00307] Rollout worker 1 uses device cpu
|
7908 |
+
[2024-09-01 10:33:31,738][00307] Rollout worker 2 uses device cpu
|
7909 |
+
[2024-09-01 10:33:31,741][00307] Rollout worker 3 uses device cpu
|
7910 |
+
[2024-09-01 10:33:31,746][00307] Rollout worker 4 uses device cpu
|
7911 |
+
[2024-09-01 10:33:31,750][00307] Rollout worker 5 uses device cpu
|
7912 |
+
[2024-09-01 10:33:31,752][00307] Rollout worker 6 uses device cpu
|
7913 |
+
[2024-09-01 10:33:31,755][00307] Rollout worker 7 uses device cpu
|
7914 |
+
[2024-09-01 10:33:31,963][00307] InferenceWorker_p0-w0: min num requests: 2
|
7915 |
+
[2024-09-01 10:33:32,035][00307] Starting all processes...
|
7916 |
+
[2024-09-01 10:33:32,043][00307] Starting process learner_proc0
|
7917 |
+
[2024-09-01 10:33:32,128][00307] Starting all processes...
|
7918 |
+
[2024-09-01 10:33:32,201][00307] Starting process inference_proc0-0
|
7919 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc0
|
7920 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc1
|
7921 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc2
|
7922 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc3
|
7923 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc4
|
7924 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc5
|
7925 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc6
|
7926 |
+
[2024-09-01 10:33:32,209][00307] Starting process rollout_proc7
|
7927 |
+
[2024-09-01 10:33:50,188][65187] Worker 0 uses CPU cores [0]
|
7928 |
+
[2024-09-01 10:33:50,798][65174] Starting seed is not provided
|
7929 |
+
[2024-09-01 10:33:50,798][65174] Initializing actor-critic model on device cpu
|
7930 |
+
[2024-09-01 10:33:50,799][65174] RunningMeanStd input shape: (3, 72, 128)
|
7931 |
+
[2024-09-01 10:33:50,802][65174] RunningMeanStd input shape: (1,)
|
7932 |
+
[2024-09-01 10:33:50,882][65174] ConvEncoder: input_channels=3
|
7933 |
+
[2024-09-01 10:33:50,946][65192] Worker 4 uses CPU cores [0]
|
7934 |
+
[2024-09-01 10:33:50,959][65191] Worker 3 uses CPU cores [1]
|
7935 |
+
[2024-09-01 10:33:50,978][65189] Worker 1 uses CPU cores [1]
|
7936 |
+
[2024-09-01 10:33:51,023][65195] Worker 7 uses CPU cores [1]
|
7937 |
+
[2024-09-01 10:33:51,154][65194] Worker 5 uses CPU cores [1]
|
7938 |
+
[2024-09-01 10:33:51,472][65190] Worker 2 uses CPU cores [0]
|
7939 |
+
[2024-09-01 10:33:51,492][65193] Worker 6 uses CPU cores [0]
|
7940 |
+
[2024-09-01 10:33:51,611][65174] Conv encoder output size: 512
|
7941 |
+
[2024-09-01 10:33:51,612][65174] Policy head output size: 512
|
7942 |
+
[2024-09-01 10:33:51,668][65174] Created Actor Critic model with architecture:
|
7943 |
+
[2024-09-01 10:33:51,676][65174] ActorCriticSharedWeights(
|
7944 |
+
(obs_normalizer): ObservationNormalizer(
|
7945 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
7946 |
+
(running_mean_std): ModuleDict(
|
7947 |
+
(obs): RunningMeanStdInPlace()
|
7948 |
+
)
|
7949 |
+
)
|
7950 |
+
)
|
7951 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
7952 |
+
(encoder): VizdoomEncoder(
|
7953 |
+
(basic_encoder): ConvEncoder(
|
7954 |
+
(enc): RecursiveScriptModule(
|
7955 |
+
original_name=ConvEncoderImpl
|
7956 |
+
(conv_head): RecursiveScriptModule(
|
7957 |
+
original_name=Sequential
|
7958 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
7959 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
7960 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
7961 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
7962 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
7963 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
7964 |
+
)
|
7965 |
+
(mlp_layers): RecursiveScriptModule(
|
7966 |
+
original_name=Sequential
|
7967 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
7968 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
7969 |
+
)
|
7970 |
+
)
|
7971 |
+
)
|
7972 |
+
)
|
7973 |
+
(core): ModelCoreRNN(
|
7974 |
+
(core): GRU(512, 512)
|
7975 |
+
)
|
7976 |
+
(decoder): MlpDecoder(
|
7977 |
+
(mlp): Identity()
|
7978 |
+
)
|
7979 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
7980 |
+
(action_parameterization): ActionParameterizationDefault(
|
7981 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
7982 |
+
)
|
7983 |
+
)
|
7984 |
+
[2024-09-01 10:33:51,963][00307] Heartbeat connected on InferenceWorker_p0-w0
|
7985 |
+
[2024-09-01 10:33:51,978][00307] Heartbeat connected on RolloutWorker_w0
|
7986 |
+
[2024-09-01 10:33:51,991][00307] Heartbeat connected on RolloutWorker_w1
|
7987 |
+
[2024-09-01 10:33:52,002][00307] Heartbeat connected on RolloutWorker_w2
|
7988 |
+
[2024-09-01 10:33:52,007][00307] Heartbeat connected on RolloutWorker_w3
|
7989 |
+
[2024-09-01 10:33:52,016][00307] Heartbeat connected on RolloutWorker_w4
|
7990 |
+
[2024-09-01 10:33:52,021][00307] Heartbeat connected on RolloutWorker_w5
|
7991 |
+
[2024-09-01 10:33:52,029][00307] Heartbeat connected on RolloutWorker_w6
|
7992 |
+
[2024-09-01 10:33:52,035][00307] Heartbeat connected on RolloutWorker_w7
|
7993 |
+
[2024-09-01 10:33:52,927][00307] Heartbeat connected on Batcher_0
|
7994 |
+
[2024-09-01 10:33:52,949][65174] Using optimizer <class 'torch.optim.adam.Adam'>
|
7995 |
+
[2024-09-01 10:33:52,951][65174] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000002932_12009472.pth...
|
7996 |
+
[2024-09-01 10:33:53,010][65174] Loading model from checkpoint
|
7997 |
+
[2024-09-01 10:33:53,058][65174] Loaded experiment state at self.train_step=2932, self.env_steps=12009472
|
7998 |
+
[2024-09-01 10:33:53,058][65174] Initialized policy 0 weights for model version 2932
|
7999 |
+
[2024-09-01 10:33:53,064][65188] RunningMeanStd input shape: (3, 72, 128)
|
8000 |
+
[2024-09-01 10:33:53,066][65174] LearnerWorker_p0 finished initialization!
|
8001 |
+
[2024-09-01 10:33:53,067][00307] Heartbeat connected on LearnerWorker_p0
|
8002 |
+
[2024-09-01 10:33:53,072][65188] RunningMeanStd input shape: (1,)
|
8003 |
+
[2024-09-01 10:33:53,098][65188] ConvEncoder: input_channels=3
|
8004 |
+
[2024-09-01 10:33:53,326][65188] Conv encoder output size: 512
|
8005 |
+
[2024-09-01 10:33:53,327][65188] Policy head output size: 512
|
8006 |
+
[2024-09-01 10:33:53,357][00307] Inference worker 0-0 is ready!
|
8007 |
+
[2024-09-01 10:33:53,359][00307] All inference workers are ready! Signal rollout workers to start!
|
8008 |
+
[2024-09-01 10:33:53,526][65187] Doom resolution: 160x120, resize resolution: (128, 72)
|
8009 |
+
[2024-09-01 10:33:53,545][65192] Doom resolution: 160x120, resize resolution: (128, 72)
|
8010 |
+
[2024-09-01 10:33:53,548][65193] Doom resolution: 160x120, resize resolution: (128, 72)
|
8011 |
+
[2024-09-01 10:33:53,555][65190] Doom resolution: 160x120, resize resolution: (128, 72)
|
8012 |
+
[2024-09-01 10:33:53,563][65191] Doom resolution: 160x120, resize resolution: (128, 72)
|
8013 |
+
[2024-09-01 10:33:53,561][65195] Doom resolution: 160x120, resize resolution: (128, 72)
|
8014 |
+
[2024-09-01 10:33:53,560][65189] Doom resolution: 160x120, resize resolution: (128, 72)
|
8015 |
+
[2024-09-01 10:33:53,566][65194] Doom resolution: 160x120, resize resolution: (128, 72)
|
8016 |
+
[2024-09-01 10:33:55,770][65187] Decorrelating experience for 0 frames...
|
8017 |
+
[2024-09-01 10:33:55,816][65192] Decorrelating experience for 0 frames...
|
8018 |
+
[2024-09-01 10:33:55,835][65193] Decorrelating experience for 0 frames...
|
8019 |
+
[2024-09-01 10:33:55,830][65189] Decorrelating experience for 0 frames...
|
8020 |
+
[2024-09-01 10:33:55,846][65195] Decorrelating experience for 0 frames...
|
8021 |
+
[2024-09-01 10:33:55,853][65191] Decorrelating experience for 0 frames...
|
8022 |
+
[2024-09-01 10:33:55,860][65190] Decorrelating experience for 0 frames...
|
8023 |
+
[2024-09-01 10:33:56,171][00307] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 12009472. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
8024 |
+
[2024-09-01 10:33:57,632][65194] Decorrelating experience for 0 frames...
|
8025 |
+
[2024-09-01 10:33:57,653][65191] Decorrelating experience for 32 frames...
|
8026 |
+
[2024-09-01 10:33:57,667][65195] Decorrelating experience for 32 frames...
|
8027 |
+
[2024-09-01 10:33:58,359][65187] Decorrelating experience for 32 frames...
|
8028 |
+
[2024-09-01 10:33:58,371][65192] Decorrelating experience for 32 frames...
|
8029 |
+
[2024-09-01 10:33:58,468][65193] Decorrelating experience for 32 frames...
|
8030 |
+
[2024-09-01 10:33:59,837][65189] Decorrelating experience for 32 frames...
|
8031 |
+
[2024-09-01 10:33:59,889][65194] Decorrelating experience for 32 frames...
|
8032 |
+
[2024-09-01 10:34:00,556][65187] Decorrelating experience for 64 frames...
|
8033 |
+
[2024-09-01 10:34:00,558][65192] Decorrelating experience for 64 frames...
|
8034 |
+
[2024-09-01 10:34:00,673][65195] Decorrelating experience for 64 frames...
|
8035 |
+
[2024-09-01 10:34:00,692][65191] Decorrelating experience for 64 frames...
|
8036 |
+
[2024-09-01 10:34:01,173][00307] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 12009472. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
8037 |
+
[2024-09-01 10:34:02,035][65194] Decorrelating experience for 64 frames...
|
8038 |
+
[2024-09-01 10:34:02,409][65191] Decorrelating experience for 96 frames...
|
8039 |
+
[2024-09-01 10:34:02,791][65193] Decorrelating experience for 64 frames...
|
8040 |
+
[2024-09-01 10:34:02,840][65190] Decorrelating experience for 32 frames...
|
8041 |
+
[2024-09-01 10:34:02,997][65192] Decorrelating experience for 96 frames...
|
8042 |
+
[2024-09-01 10:34:04,449][65189] Decorrelating experience for 64 frames...
|
8043 |
+
[2024-09-01 10:34:04,647][65194] Decorrelating experience for 96 frames...
|
8044 |
+
[2024-09-01 10:34:05,380][65187] Decorrelating experience for 96 frames...
|
8045 |
+
[2024-09-01 10:34:05,540][65193] Decorrelating experience for 96 frames...
|
8046 |
+
[2024-09-01 10:34:06,170][00307] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 12009472. Throughput: 0: 61.2. Samples: 612. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
8047 |
+
[2024-09-01 10:34:06,177][00307] Avg episode reward: [(0, '3.492')]
|
8048 |
+
[2024-09-01 10:34:07,094][65190] Decorrelating experience for 64 frames...
|
8049 |
+
[2024-09-01 10:34:07,285][65195] Decorrelating experience for 96 frames...
|
8050 |
+
[2024-09-01 10:34:07,295][65189] Decorrelating experience for 96 frames...
|
8051 |
+
[2024-09-01 10:34:10,760][65190] Decorrelating experience for 96 frames...
|
8052 |
+
[2024-09-01 10:34:11,045][65174] Signal inference workers to stop experience collection...
|
8053 |
+
[2024-09-01 10:34:11,148][65188] InferenceWorker_p0-w0: stopping experience collection
|
8054 |
+
[2024-09-01 10:34:11,170][00307] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 12009472. Throughput: 0: 105.9. Samples: 1588. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
8055 |
+
[2024-09-01 10:34:11,179][00307] Avg episode reward: [(0, '4.038')]
|
8056 |
+
[2024-09-01 10:34:13,282][65174] Signal inference workers to resume experience collection...
|
8057 |
+
[2024-09-01 10:34:13,284][65174] Stopping Batcher_0...
|
8058 |
+
[2024-09-01 10:34:13,284][65174] Loop batcher_evt_loop terminating...
|
8059 |
+
[2024-09-01 10:34:13,312][00307] Component Batcher_0 stopped!
|
8060 |
+
[2024-09-01 10:34:13,351][65188] Weights refcount: 2 0
|
8061 |
+
[2024-09-01 10:34:13,361][00307] Component InferenceWorker_p0-w0 stopped!
|
8062 |
+
[2024-09-01 10:34:13,365][65188] Stopping InferenceWorker_p0-w0...
|
8063 |
+
[2024-09-01 10:34:13,370][65188] Loop inference_proc0-0_evt_loop terminating...
|
8064 |
+
[2024-09-01 10:34:14,036][00307] Component RolloutWorker_w5 stopped!
|
8065 |
+
[2024-09-01 10:34:14,036][65194] Stopping RolloutWorker_w5...
|
8066 |
+
[2024-09-01 10:34:14,050][65194] Loop rollout_proc5_evt_loop terminating...
|
8067 |
+
[2024-09-01 10:34:14,067][00307] Component RolloutWorker_w7 stopped!
|
8068 |
+
[2024-09-01 10:34:14,072][00307] Component RolloutWorker_w3 stopped!
|
8069 |
+
[2024-09-01 10:34:14,080][65191] Stopping RolloutWorker_w3...
|
8070 |
+
[2024-09-01 10:34:14,081][65191] Loop rollout_proc3_evt_loop terminating...
|
8071 |
+
[2024-09-01 10:34:14,067][65195] Stopping RolloutWorker_w7...
|
8072 |
+
[2024-09-01 10:34:14,089][65195] Loop rollout_proc7_evt_loop terminating...
|
8073 |
+
[2024-09-01 10:34:14,093][00307] Component RolloutWorker_w2 stopped!
|
8074 |
+
[2024-09-01 10:34:14,099][65190] Stopping RolloutWorker_w2...
|
8075 |
+
[2024-09-01 10:34:14,101][65190] Loop rollout_proc2_evt_loop terminating...
|
8076 |
+
[2024-09-01 10:34:14,126][00307] Component RolloutWorker_w0 stopped!
|
8077 |
+
[2024-09-01 10:34:14,130][65187] Stopping RolloutWorker_w0...
|
8078 |
+
[2024-09-01 10:34:14,136][65187] Loop rollout_proc0_evt_loop terminating...
|
8079 |
+
[2024-09-01 10:34:14,192][65189] Stopping RolloutWorker_w1...
|
8080 |
+
[2024-09-01 10:34:14,192][00307] Component RolloutWorker_w1 stopped!
|
8081 |
+
[2024-09-01 10:34:14,208][65189] Loop rollout_proc1_evt_loop terminating...
|
8082 |
+
[2024-09-01 10:34:14,239][00307] Component RolloutWorker_w4 stopped!
|
8083 |
+
[2024-09-01 10:34:14,247][65192] Stopping RolloutWorker_w4...
|
8084 |
+
[2024-09-01 10:34:14,248][65192] Loop rollout_proc4_evt_loop terminating...
|
8085 |
+
[2024-09-01 10:34:14,263][00307] Component RolloutWorker_w6 stopped!
|
8086 |
+
[2024-09-01 10:34:14,267][65193] Stopping RolloutWorker_w6...
|
8087 |
+
[2024-09-01 10:34:14,267][65193] Loop rollout_proc6_evt_loop terminating...
|
8088 |
+
[2024-09-01 10:34:21,389][65174] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000002934_12017664.pth...
|
8089 |
+
[2024-09-01 10:34:21,705][65174] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000002917_11948032.pth
|
8090 |
+
[2024-09-01 10:34:21,753][65174] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000002934_12017664.pth...
|
8091 |
+
[2024-09-01 10:34:22,098][65174] Stopping LearnerWorker_p0...
|
8092 |
+
[2024-09-01 10:34:22,100][65174] Loop learner_proc0_evt_loop terminating...
|
8093 |
+
[2024-09-01 10:34:22,101][00307] Component LearnerWorker_p0 stopped!
|
8094 |
+
[2024-09-01 10:34:22,120][00307] Waiting for process learner_proc0 to stop...
|
8095 |
+
[2024-09-01 10:34:23,094][00307] Waiting for process inference_proc0-0 to join...
|
8096 |
+
[2024-09-01 10:34:23,107][00307] Waiting for process rollout_proc0 to join...
|
8097 |
+
[2024-09-01 10:34:23,120][00307] Waiting for process rollout_proc1 to join...
|
8098 |
+
[2024-09-01 10:34:23,130][00307] Waiting for process rollout_proc2 to join...
|
8099 |
+
[2024-09-01 10:34:23,143][00307] Waiting for process rollout_proc3 to join...
|
8100 |
+
[2024-09-01 10:34:23,152][00307] Waiting for process rollout_proc4 to join...
|
8101 |
+
[2024-09-01 10:34:23,166][00307] Waiting for process rollout_proc5 to join...
|
8102 |
+
[2024-09-01 10:34:23,178][00307] Waiting for process rollout_proc6 to join...
|
8103 |
+
[2024-09-01 10:34:23,196][00307] Waiting for process rollout_proc7 to join...
|
8104 |
+
[2024-09-01 10:34:23,214][00307] Batcher 0 profile tree view:
|
8105 |
+
batching: 0.0664, releasing_batches: 0.0005
|
8106 |
+
[2024-09-01 10:34:23,220][00307] InferenceWorker_p0-w0 profile tree view:
|
8107 |
+
update_model: 0.0290
|
8108 |
+
wait_policy: 0.0001
|
8109 |
+
wait_policy_total: 10.2431
|
8110 |
+
one_step: 0.0931
|
8111 |
+
handle_policy_step: 7.0708
|
8112 |
+
deserialize: 0.1442, stack: 0.0418, obs_to_device_normalize: 0.8121, forward: 5.4789, send_messages: 0.1427
|
8113 |
+
prepare_outputs: 0.1556
|
8114 |
+
to_cpu: 0.0223
|
8115 |
+
[2024-09-01 10:34:23,229][00307] Learner 0 profile tree view:
|
8116 |
+
misc: 0.0000, prepare_batch: 4.7974
|
8117 |
+
train: 8.9264
|
8118 |
+
epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0002, kl_divergence: 0.0007, after_optimizer: 0.0078
|
8119 |
+
calculate_losses: 3.4527
|
8120 |
+
losses_init: 0.0000, forward_head: 3.1163, bptt_initial: 0.0080, tail: 0.0106, advantages_returns: 0.0028, losses: 0.0030
|
8121 |
+
bptt: 0.3114
|
8122 |
+
bptt_forward_core: 0.3103
|
8123 |
+
update: 5.4628
|
8124 |
+
clip: 0.0221
|
8125 |
+
[2024-09-01 10:34:23,235][00307] RolloutWorker_w0 profile tree view:
|
8126 |
+
wait_for_trajectories: 0.0115, enqueue_policy_requests: 0.1034, env_step: 2.8720, overhead: 0.1024, complete_rollouts: 0.0464
|
8127 |
+
save_policy_outputs: 0.0846
|
8128 |
+
split_output_tensors: 0.0340
|
8129 |
+
[2024-09-01 10:34:23,244][00307] RolloutWorker_w7 profile tree view:
|
8130 |
+
wait_for_trajectories: 0.0249, enqueue_policy_requests: 0.0434, env_step: 1.8572, overhead: 0.0427, complete_rollouts: 0.0754
|
8131 |
+
save_policy_outputs: 0.0636
|
8132 |
+
split_output_tensors: 0.0064
|
8133 |
+
[2024-09-01 10:34:23,252][00307] Loop Runner_EvtLoop terminating...
|
8134 |
+
[2024-09-01 10:34:23,286][00307] Runner profile tree view:
|
8135 |
+
main_loop: 51.2513
|
8136 |
+
[2024-09-01 10:34:23,294][00307] Collected {0: 12017664}, FPS: 159.8
|
8137 |
+
[2024-09-01 10:52:55,466][00307] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
8138 |
+
[2024-09-01 10:52:55,468][00307] Overriding arg 'num_workers' with value 1 passed from command line
|
8139 |
+
[2024-09-01 10:52:55,474][00307] Adding new argument 'no_render'=True that is not in the saved config file!
|
8140 |
+
[2024-09-01 10:52:55,477][00307] Adding new argument 'save_video'=True that is not in the saved config file!
|
8141 |
+
[2024-09-01 10:52:55,481][00307] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
8142 |
+
[2024-09-01 10:52:55,483][00307] Adding new argument 'video_name'=None that is not in the saved config file!
|
8143 |
+
[2024-09-01 10:52:55,485][00307] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
8144 |
+
[2024-09-01 10:52:55,490][00307] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
8145 |
+
[2024-09-01 10:52:55,491][00307] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
8146 |
+
[2024-09-01 10:52:55,492][00307] Adding new argument 'hf_repository'='jarski/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
8147 |
+
[2024-09-01 10:52:55,494][00307] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
8148 |
+
[2024-09-01 10:52:55,495][00307] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
8149 |
+
[2024-09-01 10:52:55,496][00307] Adding new argument 'train_script'=None that is not in the saved config file!
|
8150 |
+
[2024-09-01 10:52:55,498][00307] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
8151 |
+
[2024-09-01 10:52:55,499][00307] Using frameskip 1 and render_action_repeat=4 for evaluation
|
8152 |
+
[2024-09-01 10:52:55,523][00307] RunningMeanStd input shape: (3, 72, 128)
|
8153 |
+
[2024-09-01 10:52:55,525][00307] RunningMeanStd input shape: (1,)
|
8154 |
+
[2024-09-01 10:52:55,546][00307] ConvEncoder: input_channels=3
|
8155 |
+
[2024-09-01 10:52:55,598][00307] Conv encoder output size: 512
|
8156 |
+
[2024-09-01 10:52:55,601][00307] Policy head output size: 512
|
8157 |
+
[2024-09-01 10:52:55,621][00307] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000002934_12017664.pth...
|
8158 |
+
[2024-09-01 10:52:56,283][00307] Num frames 100...
|
8159 |
+
[2024-09-01 10:52:56,587][00307] Num frames 200...
|
8160 |
+
[2024-09-01 10:52:56,857][00307] Num frames 300...
|
8161 |
+
[2024-09-01 10:52:57,133][00307] Num frames 400...
|
8162 |
+
[2024-09-01 10:52:57,406][00307] Num frames 500...
|
8163 |
+
[2024-09-01 10:52:57,683][00307] Num frames 600...
|
8164 |
+
[2024-09-01 10:52:57,954][00307] Num frames 700...
|
8165 |
+
[2024-09-01 10:52:58,248][00307] Num frames 800...
|
8166 |
+
[2024-09-01 10:52:58,531][00307] Num frames 900...
|
8167 |
+
[2024-09-01 10:52:58,817][00307] Num frames 1000...
|
8168 |
+
[2024-09-01 10:52:59,088][00307] Num frames 1100...
|
8169 |
+
[2024-09-01 10:52:59,369][00307] Num frames 1200...
|
8170 |
+
[2024-09-01 10:52:59,597][00307] Num frames 1300...
|
8171 |
+
[2024-09-01 10:52:59,823][00307] Avg episode rewards: #0: 37.810, true rewards: #0: 13.810
|
8172 |
+
[2024-09-01 10:52:59,825][00307] Avg episode reward: 37.810, avg true_objective: 13.810
|
8173 |
+
[2024-09-01 10:52:59,864][00307] Num frames 1400...
|
8174 |
+
[2024-09-01 10:53:00,085][00307] Num frames 1500...
|
8175 |
+
[2024-09-01 10:53:00,288][00307] Num frames 1600...
|
8176 |
+
[2024-09-01 10:53:00,488][00307] Num frames 1700...
|
8177 |
+
[2024-09-01 10:53:00,686][00307] Num frames 1800...
|
8178 |
+
[2024-09-01 10:53:00,892][00307] Num frames 1900...
|
8179 |
+
[2024-09-01 10:53:01,090][00307] Num frames 2000...
|
8180 |
+
[2024-09-01 10:53:01,300][00307] Num frames 2100...
|
8181 |
+
[2024-09-01 10:53:01,494][00307] Num frames 2200...
|
8182 |
+
[2024-09-01 10:53:01,709][00307] Num frames 2300...
|
8183 |
+
[2024-09-01 10:53:01,929][00307] Num frames 2400...
|
8184 |
+
[2024-09-01 10:53:02,163][00307] Num frames 2500...
|
8185 |
+
[2024-09-01 10:53:02,381][00307] Num frames 2600...
|
8186 |
+
[2024-09-01 10:53:02,591][00307] Num frames 2700...
|
8187 |
+
[2024-09-01 10:53:02,843][00307] Num frames 2800...
|
8188 |
+
[2024-09-01 10:53:03,050][00307] Num frames 2900...
|
8189 |
+
[2024-09-01 10:53:03,252][00307] Num frames 3000...
|
8190 |
+
[2024-09-01 10:53:03,451][00307] Num frames 3100...
|
8191 |
+
[2024-09-01 10:53:03,653][00307] Num frames 3200...
|
8192 |
+
[2024-09-01 10:53:03,865][00307] Num frames 3300...
|
8193 |
+
[2024-09-01 10:53:03,967][00307] Avg episode rewards: #0: 45.089, true rewards: #0: 16.590
|
8194 |
+
[2024-09-01 10:53:03,969][00307] Avg episode reward: 45.089, avg true_objective: 16.590
|
8195 |
+
[2024-09-01 10:53:04,125][00307] Num frames 3400...
|
8196 |
+
[2024-09-01 10:53:04,327][00307] Num frames 3500...
|
8197 |
+
[2024-09-01 10:53:04,528][00307] Num frames 3600...
|
8198 |
+
[2024-09-01 10:53:04,661][00307] Avg episode rewards: #0: 31.460, true rewards: #0: 12.127
|
8199 |
+
[2024-09-01 10:53:04,663][00307] Avg episode reward: 31.460, avg true_objective: 12.127
|
8200 |
+
[2024-09-01 10:53:04,780][00307] Num frames 3700...
|
8201 |
+
[2024-09-01 10:53:05,006][00307] Num frames 3800...
|
8202 |
+
[2024-09-01 10:53:05,215][00307] Num frames 3900...
|
8203 |
+
[2024-09-01 10:53:05,416][00307] Num frames 4000...
|
8204 |
+
[2024-09-01 10:53:05,618][00307] Num frames 4100...
|
8205 |
+
[2024-09-01 10:53:05,713][00307] Avg episode rewards: #0: 26.045, true rewards: #0: 10.295
|
8206 |
+
[2024-09-01 10:53:05,716][00307] Avg episode reward: 26.045, avg true_objective: 10.295
|
8207 |
+
[2024-09-01 10:53:05,879][00307] Num frames 4200...
|
8208 |
+
[2024-09-01 10:53:06,092][00307] Num frames 4300...
|
8209 |
+
[2024-09-01 10:53:06,303][00307] Num frames 4400...
|
8210 |
+
[2024-09-01 10:53:06,502][00307] Num frames 4500...
|
8211 |
+
[2024-09-01 10:53:06,705][00307] Num frames 4600...
|
8212 |
+
[2024-09-01 10:53:06,904][00307] Num frames 4700...
|
8213 |
+
[2024-09-01 10:53:07,118][00307] Num frames 4800...
|
8214 |
+
[2024-09-01 10:53:07,332][00307] Num frames 4900...
|
8215 |
+
[2024-09-01 10:53:07,534][00307] Num frames 5000...
|
8216 |
+
[2024-09-01 10:53:07,728][00307] Num frames 5100...
|
8217 |
+
[2024-09-01 10:53:07,852][00307] Avg episode rewards: #0: 25.470, true rewards: #0: 10.270
|
8218 |
+
[2024-09-01 10:53:07,853][00307] Avg episode reward: 25.470, avg true_objective: 10.270
|
8219 |
+
[2024-09-01 10:53:07,985][00307] Num frames 5200...
|
8220 |
+
[2024-09-01 10:53:08,188][00307] Num frames 5300...
|
8221 |
+
[2024-09-01 10:53:08,392][00307] Num frames 5400...
|
8222 |
+
[2024-09-01 10:53:08,586][00307] Num frames 5500...
|
8223 |
+
[2024-09-01 10:53:08,741][00307] Avg episode rewards: #0: 22.252, true rewards: #0: 9.252
|
8224 |
+
[2024-09-01 10:53:08,744][00307] Avg episode reward: 22.252, avg true_objective: 9.252
|
8225 |
+
[2024-09-01 10:53:08,844][00307] Num frames 5600...
|
8226 |
+
[2024-09-01 10:53:09,061][00307] Num frames 5700...
|
8227 |
+
[2024-09-01 10:53:09,259][00307] Num frames 5800...
|
8228 |
+
[2024-09-01 10:53:09,397][00307] Avg episode rewards: #0: 19.913, true rewards: #0: 8.341
|
8229 |
+
[2024-09-01 10:53:09,400][00307] Avg episode reward: 19.913, avg true_objective: 8.341
|
8230 |
+
[2024-09-01 10:53:09,555][00307] Num frames 5900...
|
8231 |
+
[2024-09-01 10:53:09,838][00307] Num frames 6000...
|
8232 |
+
[2024-09-01 10:53:10,124][00307] Num frames 6100...
|
8233 |
+
[2024-09-01 10:53:10,393][00307] Num frames 6200...
|
8234 |
+
[2024-09-01 10:53:10,661][00307] Num frames 6300...
|
8235 |
+
[2024-09-01 10:53:10,926][00307] Num frames 6400...
|
8236 |
+
[2024-09-01 10:53:11,226][00307] Num frames 6500...
|
8237 |
+
[2024-09-01 10:53:11,501][00307] Num frames 6600...
|
8238 |
+
[2024-09-01 10:53:11,778][00307] Num frames 6700...
|
8239 |
+
[2024-09-01 10:53:12,056][00307] Num frames 6800...
|
8240 |
+
[2024-09-01 10:53:12,357][00307] Num frames 6900...
|
8241 |
+
[2024-09-01 10:53:12,637][00307] Num frames 7000...
|
8242 |
+
[2024-09-01 10:53:12,863][00307] Num frames 7100...
|
8243 |
+
[2024-09-01 10:53:13,026][00307] Avg episode rewards: #0: 21.439, true rewards: #0: 8.939
|
8244 |
+
[2024-09-01 10:53:13,029][00307] Avg episode reward: 21.439, avg true_objective: 8.939
|
8245 |
+
[2024-09-01 10:53:13,127][00307] Num frames 7200...
|
8246 |
+
[2024-09-01 10:53:13,345][00307] Num frames 7300...
|
8247 |
+
[2024-09-01 10:53:13,540][00307] Num frames 7400...
|
8248 |
+
[2024-09-01 10:53:13,746][00307] Num frames 7500...
|
8249 |
+
[2024-09-01 10:53:13,952][00307] Num frames 7600...
|
8250 |
+
[2024-09-01 10:53:14,157][00307] Num frames 7700...
|
8251 |
+
[2024-09-01 10:53:14,373][00307] Num frames 7800...
|
8252 |
+
[2024-09-01 10:53:14,583][00307] Num frames 7900...
|
8253 |
+
[2024-09-01 10:53:14,780][00307] Num frames 8000...
|
8254 |
+
[2024-09-01 10:53:14,982][00307] Num frames 8100...
|
8255 |
+
[2024-09-01 10:53:15,186][00307] Num frames 8200...
|
8256 |
+
[2024-09-01 10:53:15,403][00307] Num frames 8300...
|
8257 |
+
[2024-09-01 10:53:15,607][00307] Num frames 8400...
|
8258 |
+
[2024-09-01 10:53:15,726][00307] Avg episode rewards: #0: 22.146, true rewards: #0: 9.368
|
8259 |
+
[2024-09-01 10:53:15,728][00307] Avg episode reward: 22.146, avg true_objective: 9.368
|
8260 |
+
[2024-09-01 10:53:15,880][00307] Num frames 8500...
|
8261 |
+
[2024-09-01 10:53:16,088][00307] Num frames 8600...
|
8262 |
+
[2024-09-01 10:53:16,311][00307] Num frames 8700...
|
8263 |
+
[2024-09-01 10:53:16,522][00307] Num frames 8800...
|
8264 |
+
[2024-09-01 10:53:16,719][00307] Num frames 8900...
|
8265 |
+
[2024-09-01 10:53:16,927][00307] Num frames 9000...
|
8266 |
+
[2024-09-01 10:53:17,154][00307] Num frames 9100...
|
8267 |
+
[2024-09-01 10:53:17,379][00307] Num frames 9200...
|
8268 |
+
[2024-09-01 10:53:17,574][00307] Num frames 9300...
|
8269 |
+
[2024-09-01 10:53:17,761][00307] Num frames 9400...
|
8270 |
+
[2024-09-01 10:53:17,960][00307] Num frames 9500...
|
8271 |
+
[2024-09-01 10:53:18,175][00307] Num frames 9600...
|
8272 |
+
[2024-09-01 10:53:18,391][00307] Num frames 9700...
|
8273 |
+
[2024-09-01 10:53:18,595][00307] Num frames 9800...
|
8274 |
+
[2024-09-01 10:53:18,812][00307] Num frames 9900...
|
8275 |
+
[2024-09-01 10:53:19,017][00307] Num frames 10000...
|
8276 |
+
[2024-09-01 10:53:19,226][00307] Num frames 10100...
|
8277 |
+
[2024-09-01 10:53:19,444][00307] Num frames 10200...
|
8278 |
+
[2024-09-01 10:53:19,650][00307] Num frames 10300...
|
8279 |
+
[2024-09-01 10:53:19,850][00307] Num frames 10400...
|
8280 |
+
[2024-09-01 10:53:20,057][00307] Num frames 10500...
|
8281 |
+
[2024-09-01 10:53:20,175][00307] Avg episode rewards: #0: 25.831, true rewards: #0: 10.531
|
8282 |
+
[2024-09-01 10:53:20,178][00307] Avg episode reward: 25.831, avg true_objective: 10.531
|
8283 |
+
[2024-09-01 10:54:35,854][00307] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|