Hugging Face's logo

Nablaaa
/
ppo-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Nablaaa commited on
Commit
8b82f17
·
verified ·
1 Parent(s): 1703efd

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-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. ppo-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. ppo-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. ppo-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +0 -0
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 161.50 +/- 114.26
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 256),
72
  ('n_envs', 8),
73
  ('n_epochs', 4),
74
  ('n_steps', 128),
75
- ('n_timesteps', 100000.0),
76
  ('normalize', False),
77
  ('policy', 'CnnPolicy'),
78
  ('vf_coef', 0.5)])
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 212.50 +/- 113.80
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('n_envs', 8),
73
  ('n_epochs', 4),
74
  ('n_steps', 128),
75
+ ('n_timesteps', 1000000.0),
76
  ('normalize', False),
77
  ('policy', 'CnnPolicy'),
78
  ('vf_coef', 0.5)])
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3725501010
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2026491491
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - n_steps
19
  - 128
20
  - - n_timesteps
21
- - 100000.0
22
  - - normalize
23
  - false
24
  - - policy
 
18
  - - n_steps
19
  - 128
20
  - - n_timesteps
21
+ - 1000000.0
22
  - - normalize
23
  - false
24
  - - policy
ppo-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a88e194d73757ec4bf39e2181a4365472c154d7b5eda4e48fb7ec2a0577749b
3
- size 20442946
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8272e725dd58ce7aa985965d381f7129bdde437b7ccc6b17eec7e8382e654299
3
+ size 20442950
ppo-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
ppo-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfaf729e499a422aa4199ee9c9dde68a99b95b70191aca008dec8594af9bbf41
3
  size 13511978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029d1725d9b1ab532e284c86664a9b22832c930c8cf0281b870421e20844f4e9
3
  size 13511978
ppo-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a6b6c72baeb71aa612773dc4faf861712948201b33525c67e31331d1e164bcd
3
  size 6758258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce5b021cbf59dd15dfd897f7e27a4cbcef2ca5e4af55b139622827b77bde8ec
3
  size 6758258
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 161.5, "std_reward": 114.25957290310515, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-30T06:32:00.313474"}
 
1
+ {"mean_reward": 212.5, "std_reward": 113.80355881957296, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-30T07:58:11.592752"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad34f19864d067f13853f0ef722987b153a379458fb7fec298db05065955cc19
3
- size 7049
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f17397537c3aad792ab300bd3d12852b998869e0c81952eddbf5f9f2bc35537
3
+ size 50775