Hugging Face's logo

user87441257
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
user87441257 commited on
Commit
ce24e79
•
1 Parent(s): c769d78

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,12 +67,12 @@ OrderedDict([('batch_size', 32),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 20000.0),
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: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.2),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1917621100
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3970115573
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 20000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000.0
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:b3596b172834958c239d0f218d9e1fe39c2cce4d3ef2884796ebdf88ade4006f
3
- size 13713176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf5d0000a1d1ec5854898e94ba853857eda308950a613962a730f74cda880ca
3
+ size 13712351
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 sha256:18f3197009af61cded943d9ba0b37c61e949bbe44e1fcc829450aecc65905a4a
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83170c7088d806e3f0276c195c751723c7882737448ffff803d4bb4dca07aaa3
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e402fa68302f9262ebfd7be784ce6ff6785b68f25d4aa3a86e2c515a7bbb11
3
- size 242628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961ab6016871f866ed78c92d21ef7930dec0110e72144703e0be2b439e42e1af
3
+ size 267942
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-25T11:09:42.525150"}
 
1
+ {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-25T11:18:22.109370"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d667ed36abcc9503cb4788bf0e58fa597f9e1f3591c3000008eed8a4e25d3fe
3
- size 1055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021c99fcc1f3e754ae7f2339b396422c3ff3398230452eb3f34f94bbdd66f6c1
3
+ size 628