Hugging Face's logo

Chiz
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Chiz commited on
Commit
a8f44ef
·
verified ·
1 Parent(s): 65b4ea3

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +2 -2
  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. 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: 677.00 +/- 187.85
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 32),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
- ('learning_rate', 0.0001),
75
- ('learning_starts', 10000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 484.00 +/- 185.56
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 64),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 0.00015),
75
+ ('learning_starts', 20000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -56,13 +56,13 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1584594405
60
  - - storage
61
  - null
62
  - - study_name
63
  - null
64
  - - tensorboard_log
65
- - ''
66
  - - track
67
  - false
68
  - - trained_agent
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2280447006
60
  - - storage
61
  - null
62
  - - study_name
63
  - null
64
  - - tensorboard_log
65
+ - logs/
66
  - - track
67
  - false
68
  - - trained_agent
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -14,9 +14,9 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.00015
18
  - - learning_starts
19
+ - 20000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84401f3c1685869097c94e2e6dbce5bda7f7b1877fb7e32b5c5b15e3a41e2f21
3
- size 27219600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685dd32c6c002f9e394c270cc7ef197bf67deb9b875386938657f0296b5cede7
3
+ size 27219632
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 sha256:161312087ad2a16899c03609343c9d62bb18c8c8c4d04ce6c1cdc9638784f9a2
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bdc1246e4306fc648acadd785670ae2414f1258866751b4bef694e7bb56429
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e12479bfe7fa8506dbacc1e0076a82103b8858abc3bf5eff035feaed81cdd90
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb623bb56662418b74b0586427cc6c65acb674c077d8aa38366eef9f64a8f38
3
  size 13505767
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 677.0, "std_reward": 187.8456813450871, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-27T17:52:01.423694"}
 
1
+ {"mean_reward": 484.0, "std_reward": 185.5640051303054, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-29T16:07:36.908336"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29c9a91330e924aeb03f3d877300b38203817a4ab292b6a08bebcd2f157a9f97
3
- size 34985
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec69916b9b7386550d15093bf138ef9b0438a9a272feca79f15314414959fe9
3
+ size 35570