Hugging Face's logo

sErial03
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
sErial03 commited on
Commit
c1e1bb5
·
verified ·
1 Parent(s): 2a1d5fb

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  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: 243.50 +/- 57.01
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -64,7 +64,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
- ('buffer_size', 10000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
@@ -72,11 +72,11 @@ OrderedDict([('batch_size', 32),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
- ('learning_starts', 10000),
76
- ('n_timesteps', 100000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
- ('target_update_interval', 100),
80
  ('train_freq', 4),
81
  ('normalize', False)])
82
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 626.50 +/- 243.39
20
  name: mean_reward
21
  verified: false
22
  ---
 
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
+ ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
 
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
+ ('learning_starts', 100000),
76
+ ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
+ ('target_update_interval', 1000),
80
  ('train_freq', 4),
81
  ('normalize', False)])
82
  ```
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 183866112
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3928331250
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -16,14 +16,14 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - 100
28
  - - train_freq
29
  - 4
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
+ - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
+ - 1000
28
  - - train_freq
29
  - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:907fc147e5f0da15501f6e6fc5db8ff398c535730c25f44eb60a327b7d178219
3
- size 27220632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d6e6f3a67c1fac750d6936811cd63751c3a271e2a594a91a9dbb94d1c96e79
3
+ size 27220639
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 sha256:1e01fcc77a748adae7e872da5594a4e960f8114b2db9a99e0ee3b6b985393c18
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7f20900c2fcd01eabbe63eca4888a57e0fd71e30071729ea849efe3352c303
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f71496c2ed4da780a77759a3120d39ae35004ff492454077c8370a9c164de1a1
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7762324fbebcd52f6d1367795a8d026382ff6cbd7e34896ed5a3ae6a5a6e66
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 243.5, "std_reward": 57.01096385784054, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-31T06:55:19.396211"}
 
1
+ {"mean_reward": 626.5, "std_reward": 243.39320039803906, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-31T09:24:48.688397"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e28387adbc9a2fc3b4ab8dcf5f5b4d4274ab67206b35cbc05b93923634ebfc8
3
- size 4956
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4066b31ad6b5bb240709e06229e16719699d0475e5c1d5ed1b2764dd53bb71b
3
+ size 36153