Hugging Face's logo

jliu596
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
jliu596 commited on
Commit
8d47838
·
1 Parent(s): 4228eb9

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  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: 163.50 +/- 34.72
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,15 +62,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 64),
66
  ('buffer_size', 1000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.5),
70
  ('exploration_fraction', 1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
  ('learning_starts', 1000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 178.50 +/- 157.47
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
  ('buffer_size', 1000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.05),
70
  ('exploration_fraction', 1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 1000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 4072161153
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4084644614
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,12 +1,12 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
  - 1000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.5
10
  - - exploration_fraction
11
  - 1
12
  - - frame_stack
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 1000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
4
  - - buffer_size
5
  - 1000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.05
10
  - - exploration_fraction
11
  - 1
12
  - - frame_stack
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 1000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1d1f2a8c0f3586754fa701ed0b480aab4ff406ab9730482241660d5192d9190
3
- size 27218366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a01f82e2e21f00b88021f80f57c52d00f4f0fb2fb340c6f67440be10d75fc5
3
+ size 27218385
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:c0a3d964c1178fde7a6b63740b0105963620891a449a1ac561ddf3620c45993f
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f96e67dfa30950706c1bb5651cc76b6974939c7b75e1289199c4b757e9b5b5
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:924b9dcd55124d23936883f683e5c6b4bb231b43c32e52011c3c179922b7a730
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ccee755a3e6e35086544de99352df41e4b91be4264af751cef16483a39b8ba1
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c770163c90b14dd48b034d05e636471c65b483c1b322dbe51a48a780ade1edb
3
- size 263363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16b2ef1bf6c348dcd0c313dd9095818c8c6e17a48c95c0834722babd2644f7d
3
+ size 286968
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 163.5, "std_reward": 34.7167106736799, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-17T19:48:49.877603"}
 
1
+ {"mean_reward": 178.5, "std_reward": 157.46507549294859, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-17T21:16:49.576883"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3276e7e1599db5d2e62f357a9b4f37d28404e91c2d0fe03ca879fd9ef06840ab
3
- size 49381
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb7a4f1b50923a0c3e037d0c900f63b9e830de3135081f5e57497208177c8a1
3
+ size 47226