Hugging Face's logo

jroblesgomez
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
jroblesgomez commited on
Commit
853dcf3
•
1 Parent(s): 0419aec

Initial commit

Browse files
Files changed (12) 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/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +3 -3
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 284.50 +/- 111.28
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', 1000000.0),
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: 617.50 +/- 130.27
20
  name: mean_reward
21
  verified: false
22
  ---
 
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
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1382724164
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 4190665902
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
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:fa0148bd5b38b702aedca08e0714beecb494aaa03539a6e5641856656bf12ef5
3
- size 27220792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1adc34a3b90148b1ee1f211bb5e072e9a90216d5725b2ef0fc2da16255d13d17
3
+ size 27220725
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.4.0a4
 
1
+ 2.4.0a6
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:d49df4262db46495343ceb5468712772c4ea39151f8a04b02f7b8407b1afc1c4
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4f66a36d9dc923041c2f1574bef9c4427138264df8ffa63b733d2b074bb306
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12086cb45959d0bbe99045905e10850b627fae8c734e0f6cf02f2fbbbc81ac7d
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ca9cef1d1fb833ec7639b408fbbf2b08d848597585e100afd3635ecc0414a6
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Tue Jun 18 14:18:04 UTC 2024
2
  - Python: 3.10.12
3
- - Stable-Baselines3: 2.4.0a4
4
- - PyTorch: 2.3.0+cu121
5
  - GPU Enabled: True
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
  - Python: 3.10.12
3
+ - Stable-Baselines3: 2.4.0a6
4
+ - PyTorch: 2.3.1+cu121
5
  - GPU Enabled: True
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd59bb90a45e0c98acdf373be0606da052f65f1c2562e1cb40cd7aa72f363caa
3
- size 293118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05551ee572f5d0fb9994520557c20293304a63cbc5c2e5613fb31ebc280234be
3
+ size 238240
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 284.5, "std_reward": 111.27555886177342, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-03T19:08:07.576755"}
 
1
+ {"mean_reward": 617.5, "std_reward": 130.2737502338825, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-25T18:35:14.162694"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe018099aadacbaa1e3372aeb3733773d50a6d88c4325f91293cfbdc2483c117
3
- size 35280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:268b4b40b88c737e6d7416178f95ae27ae7a34c9b3412938bce9db97f06718b6
3
+ size 32256