Hugging Face's logo

sabretoothedhugs
/
dqnspaceinvader

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
sabretoothedhugs commited on
Commit
728c578
•
1 Parent(s): bbae32f

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. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/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: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 6.50 +/- 10.74
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 758.00 +/- 216.24
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2984369361
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1433755495
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4112ac0d601e2f5f6896e48298cbc312e216bd1b1744c92bada6568fc32b8011
3
- size 13715011
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2849cc1d24ec790ef54610ee9cfd19803ae7778a29f08d65924e2ce24a2b0cc
3
+ size 27220136
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423337b7e1d995354279c4a316cbb86e03a424126873f7db35f89f537fd40087
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c2fd1206dbaa2941b5d03412278a913f00b04f963fb5257af71aa9421bf3334
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1fcef05894c36f747c9e3e24e8c684e45ede1a0ab5dbc1d2d8704362a82101
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4ee3e243890b20c0adfa28ee5ec0e99992fafc39572a68f60ee9a99d62e36c7
3
- size 292612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66782391b7a26125ee03cceb2675b5a3e6e969dfc41864cb025a09f98cd2d42f
3
+ size 214384
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 6.5, "std_reward": 10.735455276791944, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-21T23:42:50.281622"}
 
1
+ {"mean_reward": 758.0, "std_reward": 216.24291895921124, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-22T13:45:09.975157"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edf9d555b416ef5370c6b0a698efb71f05d74fb06b8c1ae08651cd6e6d279079
3
- size 5730
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d58e04450457db1e01f16ded717b879879b860fded85c7f923c072e4e696bc4
3
+ size 37627