Hugging Face's logo

matheusgeda
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
matheusgeda commited on
Commit
3af6a70
•
1 Parent(s): 75deb79

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: 210.50 +/- 47.30
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', 500000),
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: 180.50 +/- 87.45
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 120000),
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
- - 1382362101
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2397659263
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 500000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 120000
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 sha256:7d5e5f7a74effa8e56f62fc3d0cff310f1a0d72cd762ef7c3e3deacd83167aca
3
- size 27217983
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6781eb8151cb86b8c03b1165122acda5c1e09eab628990f4745f9cd2369d69
3
+ size 27218488
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:e9d32a0cbd3a757c30e1d98c584ed7c4c4fb676875028a98fe325ff907f82c6e
3
- size 13505419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4497d35fe98f90c0bedeb15abc6cd3d2ca7d996ae88b62aa0de97f9cf076820
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30ee1283614b380ce9d4a86e536e2ed3c262d7ced89268358d603331576d8e5c
3
- size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99fc5637991585d9003205a001592a21d73bbbb214a6f5ed9735812153dcffc7
3
+ size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.1.0
4
  - PyTorch: 2.0.1+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: 2.1.0
4
  - PyTorch: 2.0.1+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 sha256:2fd883382206480fe454d5355a26af1789d5364006eee9803125c94f4aec5c37
3
- size 262079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803a66d53930a9c4fa52d47718be52163570d739a3e1348ecb47ff45557dad6a
3
+ size 269927
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 210.5, "std_reward": 47.29957716512908, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-10-16T20:37:21.146930"}
 
1
+ {"mean_reward": 180.5, "std_reward": 87.44855630597911, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-10-16T20:56:50.041748"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5737b714f92879d27dab9eba88e62901ad4e501ec30587264fd3b4481d9ba140
3
- size 8135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58ef5dd7de7bdb746aa426079dd5521dabacc2ad717b53f4ddd08e62275e02c1
3
+ size 6768