Hugging Face's logo

coyotespike
/
dqn-PongNoFrameskip-v4

Reinforcement Learning
stable-baselines3
PongNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
coyotespike commited on
Commit
ebb8646
•
1 Parent(s): c33706a

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-PongNoFrameskip-v4.zip +2 -2
  5. dqn-PongNoFrameskip-v4/data +0 -0
  6. dqn-PongNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-PongNoFrameskip-v4/policy.pth +1 -1
  8. dqn-PongNoFrameskip-v4/system_info.txt +4 -4
  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: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 1.00 +/- 8.43
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -65,9 +65,9 @@ OrderedDict([('batch_size', 32),
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('normalize', False),
72
  ('optimize_memory_usage', True),
73
  ('policy', 'CnnPolicy'),
 
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 19.20 +/- 1.25
20
  name: mean_reward
21
  verified: false
22
  ---
 
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 5e-05),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 2000000.0),
71
  ('normalize', False),
72
  ('optimize_memory_usage', True),
73
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3720837839
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1278136934
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - normalize
23
  - false
24
  - - optimize_memory_usage
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 5.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
22
  - - normalize
23
  - false
24
  - - optimize_memory_usage
dqn-PongNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0ba9ecfee4734f42ca2e5b1f669c3b4191e279097d740d4c325d658b8490229
3
- size 27224841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda73da3b35cc21526df4267a97b77621eb80aea33dc39a8b49599f535b88d17
3
+ size 27224973
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 sha256:9fccd2c262467eaacdcf9fda2ffe2d992b694a4e5f86b7510c944d49d78c0758
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1df10932eb38c59957d841a43d902fd2617cee25ca61cda90f03ae8b7ac571
3
  size 13505739
dqn-PongNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66daef56ae9b0bdeecf27d60910fa8a6d45979882ac46dcb42612996d5203e14
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b650c646978506a6177d0044976fdbc379b8fac277c2104b393cd92523b5c1fd
3
  size 13504937
dqn-PongNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
- Python: 3.8.16
3
  Stable-Baselines3: 1.7.0a10
4
- PyTorch: 1.13.0+cu116
5
  GPU Enabled: True
6
- Numpy: 1.21.6
7
  Gym: 0.21.0
 
1
+ OS: Linux-5.4.0-105-generic-x86_64-with-glibc2.29 #119-Ubuntu SMP Mon Mar 7 18:49:24 UTC 2022
2
+ Python: 3.8.10
3
  Stable-Baselines3: 1.7.0a10
4
+ PyTorch: 1.13.1+cu117
5
  GPU Enabled: True
6
+ Numpy: 1.19.5
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:beef9b432df85269fc4fec638bde1f2a7b534358dd6d53e8ae5ee11f9c9bdef9
3
- size 66821
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd61748b2b2e26c2a11a25a533e9a9071ede73e12c04748134696df4dca139ed
3
+ size 67204
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 1.0, "std_reward": 8.426149773176359, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-23T15:56:16.826685"}
 
1
+ {"mean_reward": 19.2, "std_reward": 1.2489995996796797, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-24T15:15:57.883594"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f34fd12e753c6a9e3e95e86b9d16074f9380eb19c29bfbfc540ce49de479fe0c
3
- size 18451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d638e1576c1aae05d7090604472596a9814c500a8d6983443b1c51a61e139f
3
+ size 29793