Hugging Face's logo

xaeroq
/
ppo-MsPacman-v5

Reinforcement Learning
stable-baselines3
ALE/MsPacman-v5
deep-reinforcement-learning
Eval Results
Model card Files Community
xaeroq commited on
Commit
738629e
·
1 Parent(s): 70d1a75

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. ppo-ALE-MsPacman-v5.zip +2 -2
  5. ppo-ALE-MsPacman-v5/data +0 -0
  6. ppo-ALE-MsPacman-v5/policy.optimizer.pth +1 -1
  7. ppo-ALE-MsPacman-v5/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: ALE/MsPacman-v5
17
  metrics:
18
  - type: mean_reward
19
- value: 600.00 +/- 273.20
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 256),
67
  ('n_envs', 8),
68
  ('n_epochs', 4),
69
  ('n_steps', 128),
70
- ('n_timesteps', 100000.0),
71
  ('policy', 'CnnPolicy'),
72
  ('vf_coef', 0.5),
73
  ('normalize', False)])
 
16
  type: ALE/MsPacman-v5
17
  metrics:
18
  - type: mean_reward
19
+ value: 2934.00 +/- 982.27
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('n_envs', 8),
68
  ('n_epochs', 4),
69
  ('n_steps', 128),
70
+ ('n_timesteps', 10000000.0),
71
  ('policy', 'CnnPolicy'),
72
  ('vf_coef', 0.5),
73
  ('normalize', False)])
args.yml CHANGED
@@ -52,7 +52,7 @@
52
  - - save_replay_buffer
53
  - false
54
  - - seed
55
- - 1957088056
56
  - - storage
57
  - null
58
  - - study_name
 
52
  - - save_replay_buffer
53
  - false
54
  - - seed
55
+ - 3847139588
56
  - - storage
57
  - null
58
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - n_steps
19
  - 128
20
  - - n_timesteps
21
- - 100000.0
22
  - - policy
23
  - CnnPolicy
24
  - - vf_coef
 
18
  - - n_steps
19
  - 128
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - policy
23
  - CnnPolicy
24
  - - vf_coef
ppo-ALE-MsPacman-v5.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:963460d73a3808a1b9392f215084a36475dc2c64f8a9a0956dbc06ac0e04bbd6
3
- size 20460412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3c9be26583b22b3682f07c044f08d11024aade7dfa19bfd8e9c3764343d275
3
+ size 20460599
ppo-ALE-MsPacman-v5/data CHANGED
The diff for this file is too large to render. See raw diff
 
ppo-ALE-MsPacman-v5/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaa38a624806115921bb6154e31ccc602cfbe7f24edb044dbae96ccb2de8e425
3
  size 13523769
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0776ae089950e1967fe59ce0e0df9dcca0a97dd3b4ef5e0c933fb80fff156a9d
3
  size 13523769
ppo-ALE-MsPacman-v5/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24363ec453853613689e8bb58d407a45e6ee6060d7d40c163eab1e44ec0f27a4
3
  size 6761153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5854ce54273331fe3981626bd3446465404e3448af63749f9d6d2ee380cbcdc4
3
  size 6761153
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b813f1446d56d84b233e9d30f53c234a4b05a5a2879b84fcdcab874617638fb7
3
- size 296608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30a860ad7b7368be8a2c905ecfb22e161174034d4f112228f96f47d6242fd7c
3
+ size 359088
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 600.0, "std_reward": 273.20322106446696, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-24T00:53:39.799849"}
 
1
+ {"mean_reward": 2934.0, "std_reward": 982.274910602933, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-24T11:46:59.324591"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d66542c2255a2b66e4d269824d379a050be792598cbbfa340af33cb0537944a5
3
- size 17914
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e309f194c14d1447cb834567cb679c6b14054c54bddb0c0a1ed4540b8276a6
3
+ size 961512