Hugging Face's logo

bsenst
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
bsenst commited on
Commit
b082082
·
1 Parent(s): 03077cf

Initial commit

Browse files
Files changed (9) 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.pth +1 -1
  7. replay.mp4 +2 -2
  8. results.json +1 -1
  9. 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: 126.50 +/- 12.05
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', 1000),
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: 15.50 +/- 12.54
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 3000),
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
- - 2175435273
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3727293767
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000
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 sha256:1e1e100132891bf5a48d8d5fd1bada5baed1db92b1df859ce53ed4ada7911ba2
3
- size 13715688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f5d6b06953c07e174547cc1391720b9de88dd41699acd6d53a6a97de1a0bd3
3
+ size 13715773
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6a6aaf9f05526101ec0e7dadad4ad561cda0448aee74a7187cc783daaf92abd
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1d4a9bf585cd13022dfbcb34755fc97e4fc9d6c5a6e0c6c3cdf8968327f19a
3
  size 13504745
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d30f425ba99fe446294f65160c71541e8bb2d80dfa84d6fe7e802ff8b95cf670
3
- size 266227
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1336777fcc82df62976f19ade9aa131a3825f788d525d0e238ee57097cf4d0c
3
+ size 272889
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 126.5, "std_reward": 12.05197079319395, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-13T02:42:53.645083"}
 
1
+ {"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-13T02:44:55.545828"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fbd11a9c5bf296728a83b911f1c5deb2de4d9162e5e1f980609c3dcaaf07345
3
- size 246
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c256140be5b6f442e2bb9b567c8a8491f27ceea5d2ecb1d36b20819e29ec5f4f
3
+ size 288