Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 483.50 +/- 180.71
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 395.50 +/- 156.84
+      name: mean_reward
+      verified: false
 ---
 
 # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
@@ -37,20 +38,26 @@ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
 
 ```
 # Download model and save it into the logs/ folder
-python -m utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga AdiKompella -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga AdiKompella -f logs/
 python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga AdiKompella -f logs/
+rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+```
+
 ## Training (with the RL Zoo)
 ```
 python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
 # Upload the model and generate video (when possible)
-python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga AdiKompella
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga AdiKompella
 ```
 
 ## Hyperparameters
 ```python
-OrderedDict([('batch_size', 32),
+OrderedDict([('batch_size', 64),
              ('buffer_size', 100000),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -61,7 +68,7 @@ OrderedDict([('batch_size', 32),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
              ('n_timesteps', 1000000.0),
-             ('optimize_memory_usage', True),
+             ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),
              ('train_freq', 4),

args.yml

@@ -1,6 +1,8 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
     - dqn
+  - - conf_file
+    - null
   - - device
     - auto
   - - env
@@ -41,6 +43,8 @@
     - null
   - - optimize_hyperparameters
     - false
+  - - progress
+    - false
   - - pruner
     - median
   - - sampler
@@ -50,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 3785032319
+    - 1833769000
   - - storage
     - null
   - - study_name
@@ -73,3 +77,5 @@
     - null
   - - wandb_project_name
     - sb3
+  - - yaml_file
+    - null

config.yml

@@ -1,6 +1,6 @@
 !!python/object/apply:collections.OrderedDict
 - - - batch_size
-    - 32
+    - 64
   - - buffer_size
     - 100000
   - - env_wrapper
@@ -20,7 +20,7 @@
   - - n_timesteps
     - 1000000.0
   - - optimize_memory_usage
-    - true
+    - false
   - - policy
     - CnnPolicy
   - - target_update_interval

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dea494b1b77497c94312d1562d3d5412d86b57aabc78309ed8ccf7b1be52a62
-size 27222203
+oid sha256:6f81d1a234d4fc397a5cdbefa9e9195e4d22c6338f6e2eee0c7799b0d51a6b8d
+size 27224794

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.5.1a8
+1.7.0a10

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9beb694283cffebfda6503ce18f7083dad85a0741dcafce3a772e6dec1758adc
-size 13503145
+oid sha256:8d80156ddb0dc200c180c51d29d03c304950d4c6ff5f5e7703bf700bebb24c62
+size 13505739

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397402417cc7b0381c998d0d96a630b28d266a05938794a6b2e187bc0eace245
+oid sha256:5015934598d25e06bb579fcdeaae5f740bd67d748bfc1359a867d34b35dd861c
 size 13504937

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -1,7 +1,7 @@
-OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
-Python: 3.7.13
-Stable-Baselines3: 1.5.1a8
-PyTorch: 1.11.0+cu113
+OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.16
+Stable-Baselines3: 1.7.0a10
+PyTorch: 1.13.0+cu116
 GPU Enabled: True
 Numpy: 1.21.6
 Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd8591ca786dff6946ac73131701efc91cbc3db84eb5af6ddea5f12d5b67bc7
-size 188033
+oid sha256:44f33f5ab6ed5e761385e87426e2edef0d996ab375df8cd7e5925479ee3028d4
+size 219303

results.json

@@ -1 +1 @@
-{"mean_reward": 483.5, "std_reward": 180.70763680597452, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T23:05:38.427677"}
+{"mean_reward": 395.5, "std_reward": 156.83510448875916, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-27T00:17:04.511357"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645878abe0df26c0c0ab326fbdb0c345c0b2ff311074fb5fedb6b9349b031d55
-size 36404
+oid sha256:aaceefd27196fd4c2feb43e060a07049716a7e17b0d830edc93f49cfae51dc55
+size 36613