Hugging Face's logo

MHaurel
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
MHaurel commited on
Commit
8ddc307
•
1 Parent(s): 8afe927

Initial commit

Browse files
Files changed (11) 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.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 301.50 +/- 128.74
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
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
- ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 300000.0),
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: 364.50 +/- 135.58
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 200000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 800000.0),
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
- - 1565772427
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1618894962
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 300000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 200000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 800000.0
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 sha256:821b918a615733b91ec01b2ca13f81f1b18de8890c4ddbbd22b94338da817970
3
- size 27224856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbefbd4ac46d0f8bdc58e0e79fd554b44bd65874e02fa1cdcc786272b4a307bd
3
+ size 27224350
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:b682db36b881fcbf31fddaee1293ba239551e1154bfefa9769bd22afbe903336
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf128d496fc1bb52b3de3aee917d3647843e0b616acbbb4dbfec70c2ba641864
3
+ size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aab0fa830350e2cb9f16210febb83a17b0ea1452916a8bb0caf2922eb3245d46
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81746afd519bca46bd356df2bf029ecdf9df497233003452524732ac4262ebe7
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,6 +2,6 @@
2
  - Python: 3.10.11
3
  - Stable-Baselines3: 1.8.0
4
  - PyTorch: 2.0.1+cu118
5
- - GPU Enabled: True
6
  - Numpy: 1.22.4
7
  - Gym: 0.21.0
 
2
  - Python: 3.10.11
3
  - Stable-Baselines3: 1.8.0
4
  - PyTorch: 2.0.1+cu118
5
+ - GPU Enabled: False
6
  - Numpy: 1.22.4
7
  - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a9f384ab3b3a571adc2268d9de2465e8847d8d40c31f32f96768083b9fae10
3
- size 256201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6230f38d44926b105c2a98445097af86b36538c86d7c895e568c4f63826ed9
3
+ size 227881
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 301.5, "std_reward": 128.744902811723, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-24T19:14:30.615058"}
 
1
+ {"mean_reward": 364.5, "std_reward": 135.58115650782744, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-27T12:30:59.498529"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7390722a09645db0aa8722be60a99d21074b5ae8cc21dd45a70c7536a3860112
3
- size 13844
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9eb676b12165777cad61b4d914f6af5a3f3f716d191c7ded73ff5ce748c99b0
3
+ size 12125