Hugging Face's logo

Adulala20
/
dqn-PongNoFrameskip-v4

Reinforcement Learning
stable-baselines3
PongNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Adulala20 commited on
Commit
b8e2053
•
1 Parent(s): 923fc37

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-PongNoFrameskip-v4.zip +2 -2
  5. dqn-PongNoFrameskip-v4/data +0 -0
  6. dqn-PongNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-PongNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: -20.90 +/- 0.30
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', 10000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: -7.00 +/- 9.43
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
- - 3328015808
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3773686184
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000.0
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-PongNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87e06b62e1c6a56002153066655c20372178b17fbde7c5cce467a5db9f502332
3
- size 13709600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad53fbc32e56dff68600b3fa1b7247c193f8e882c3bc5c1cbba99527a96931e3
3
+ size 27218384
dqn-PongNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-PongNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352862421096e10077d5b2f1a39bcd701c8dd350f71c8001e0c72fb1c678909f
3
+ size 13505739
dqn-PongNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0344bcfbfdb9f4ed4d9ecf06027f21e86dc3b636b4fb2304f1828f58cf2d2d9
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07a03f6a1bef31f42e2aa331006363a90cd3f1e44378084d373bf1a8622ca47
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f2ca9ba2e769a9f51499c33f69deb4fe955c31d6103e7e0e2f49fc27be652f3
3
- size 49725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ceaefbb718b769617bec2aea27dac8a272b22513d44be9a24867e86280ac82
3
+ size 67374
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -20.9, "std_reward": 0.3, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-09T07:19:56.894521"}
 
1
+ {"mean_reward": -7.0, "std_reward": 9.433981132056603, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-09T08:44:58.242802"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d997e9c6b0be111fd7520c9e2b1d9cb7fe9e47e225df64a1086b9d697bac3d25
3
- size 414
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fa1297aca5b4e3c0b14b2e44009862328605ec78c4d4cf252fa02141659b0c
3
+ size 19314