Hugging Face's logo

amanoyaku
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
amanoyaku commited on
Commit
8789d08
·
verified ·
1 Parent(s): 3fbc60f

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .summary/0/events.out.tfevents.1735540611.86790b443086 +3 -0
  2. .summary/0/events.out.tfevents.1735542561.86790b443086 +3 -0
  3. README.md +1 -1
  4. checkpoint_p0/best_000009753_39948288_reward_41.599.pth +3 -0
  5. checkpoint_p0/checkpoint_000009767_40005632.pth +3 -0
  6. checkpoint_p0/checkpoint_000009769_40013824.pth +3 -0
  7. config.json +3 -3
  8. replay.mp4 +2 -2
  9. sf_log.txt +0 -0
.summary/0/events.out.tfevents.1735540611.86790b443086 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ba86d6ba0a4bc4701ce8531470c4775d9253920ee95458472d064eff3b35a2
3
+ size 676843
.summary/0/events.out.tfevents.1735542561.86790b443086 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ed4ebf5aa23c7d8c8cf2d78f1429df9ccd1e804910b0490075965ef137cef8
3
+ size 2158
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 9.37 +/- 4.81
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 16.31 +/- 5.42
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000009753_39948288_reward_41.599.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8baf45e89707ff11584e57ff62e75c854647ee20e34c5f43a02c5a4ab91aaeea
3
+ size 34929243
checkpoint_p0/checkpoint_000009767_40005632.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10541f82c103ffa95131940d1b457aeb2159d00e1a3361c90159ea09303e6125
3
+ size 34929669
checkpoint_p0/checkpoint_000009769_40013824.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1cc317360f81e016a7912bb0fc9e99b409414ccffd41410e927dc3929357247
3
+ size 34929669
config.json CHANGED
@@ -15,8 +15,8 @@
15
  "worker_num_splits": 2,
16
  "policy_workers_per_policy": 1,
17
  "max_policy_lag": 1000,
18
- "num_workers": 8,
19
- "num_envs_per_worker": 4,
20
  "batch_size": 1024,
21
  "num_batches_per_epoch": 1,
22
  "num_epochs": 1,
@@ -65,7 +65,7 @@
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
- "train_for_env_steps": 4000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
 
15
  "worker_num_splits": 2,
16
  "policy_workers_per_policy": 1,
17
  "max_policy_lag": 1000,
18
+ "num_workers": 16,
19
+ "num_envs_per_worker": 8,
20
  "batch_size": 1024,
21
  "num_batches_per_epoch": 1,
22
  "num_epochs": 1,
 
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 40000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45cd84a6ee1d3017086bda38ef0acb5ecfccbdeef015939c27707b8b1652b347
3
- size 17223963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0b28b2650b7fc44dd9d35983712abea9689855b09bed5c30c23f33f8656379
3
+ size 197138454
sf_log.txt CHANGED
The diff for this file is too large to render. See raw diff