Hugging Face's logo

pokjay
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
pokjay commited on
Commit
93207b8
•
1 Parent(s): 5e5e516

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  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: 124.00 +/- 106.67
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
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: 608.50 +/- 116.53
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000.0),
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
- - 177327698
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1436834584
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:8d6810704578738f39e29ad70c13914bab3b0f38bf3814fb6fa32568b4f7dbca
3
- size 13714802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0c86677fe1d72ef89caeb38e067a9e7b9a1bff6a221dea0361bb7320896d47
3
+ size 27220118
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:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324f1d70a1752fca3f5f1bad76a81c6240a34740bc7df1d4659eefcb6573bdd0
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eb9abf81da5f0b26bbae5caa67754ccfe8124dfe8c073883cd2828e680ebeff
3
- size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e0ae85b25cf99a27a64d1bc5eacde01196d8254e8cdf2946274b864e288f6b
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.2.1
4
  - PyTorch: 2.1.0+cu118
5
- - GPU Enabled: False
6
  - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.2.1
4
  - PyTorch: 2.1.0+cu118
5
+ - GPU Enabled: True
6
  - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6993384e953a608673519dea4d345c8bc3574c3b27bbffb04574d03ee428ce60
3
- size 280310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c953e4a4097b36202b006137ce4fbc29f1886cc6fddf594938d76efe129d9c48
3
+ size 269736
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 124.0, "std_reward": 106.67239567948214, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-08T13:02:35.685889"}
 
1
+ {"mean_reward": 608.5, "std_reward": 116.53432970588538, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-08T14:42:21.384225"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fbfed2bbfb8ccb174a3fc3f436438860c582a2a856dc45692e73398d62f95f8
3
- size 5660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b56546c8781f2150e3b67a36b42d80832c97ad30ddc020888da62ccd2145b5
3
+ size 37637