Hugging Face's logo

numan966
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
numan966 commited on
Commit
ba28a1d
•
1 Parent(s): e169a91

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +2 -2
  2. args.yml +3 -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 +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +7 -7
  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: 570.50 +/- 101.11
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -65,7 +65,7 @@ OrderedDict([('batch_size', 64),
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', 2000000.0),
71
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 592.50 +/- 136.37
20
  name: mean_reward
21
  verified: false
22
  ---
 
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.0002),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 2000000.0),
71
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1895882575
58
  - - storage
59
  - null
60
  - - study_name
@@ -77,5 +77,7 @@
77
  - null
78
  - - wandb_project_name
79
  - sb3
 
 
80
  - - yaml_file
81
  - null
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2296579620
58
  - - storage
59
  - null
60
  - - study_name
 
77
  - null
78
  - - wandb_project_name
79
  - sb3
80
+ - - wandb_tags
81
+ - []
82
  - - yaml_file
83
  - null
config.yml CHANGED
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0002
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:749a1c881df1af0fa7f9118c5539d8d7c401c6b2285558ee6c25074fa3a5c0bc
3
- size 27224794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4506484710f33bef1e34f70183f985ce74d85701e30b384f59f55f0ca471831
3
+ size 27224809
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.7.0a10
 
1
+ 1.7.0a11
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:d728731cf7554e5079fe5252b3582d2320130fc1904c73f4183ded00f1cf95e6
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85064bea5a41aeb44f97f2eafffc3b87672dc9ceb00bc28335ff81d0e0f0b2f9
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:da7d6c0e0425f870cd78dabc41533afa65d0edf882d9473ff1aa77acc463286a
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017ed39eb1eb426b6b6f49e497d5f1c38985ba37f3e7aa9b7d1862df75a1053b
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-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-5.10.133+-x86_64-with-glibc2.27 # 1 SMP Fri Aug 26 08:44:51 UTC 2022
2
+ - Python: 3.8.16
3
+ - Stable-Baselines3: 1.7.0a11
4
+ - PyTorch: 1.13.0+cu116
5
+ - GPU Enabled: True
6
+ - Numpy: 1.21.6
7
+ - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05aaab6553f30de194d8f22534cf7fa8b5e71af262eb9a3e254a5a85825d76ac
3
- size 215384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1b7b48d7a458c7506e76a4103b104475ff89410da93bc3095f6c00366c4a93
3
+ size 200791
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 570.5, "std_reward": 101.10514329152598, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T18:12:55.864361"}
 
1
+ {"mean_reward": 592.5, "std_reward": 136.3680681098035, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-03T17:36:13.556761"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eac96cbc9835cf26e6e1431b227ebab7950f2707589eafce7a4c768ddc11a58a
3
- size 64444
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9113da9ba8d4a7633f7499eb1d923191b660679a7f0a1c800fa0db1348191997
3
+ size 63298