Hugging Face's logo

mojemai
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
mojemai commited on
Commit
ccf5b21
·
1 Parent(s): fa70f95

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 +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +3 -3
  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: 15.50 +/- 12.54
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,7 +70,7 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 642.50 +/- 254.36
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2164832537
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 161416888
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
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 sha256:6ef2a398310fda39d2c79ee8dda472a64427f9ade756904efd2bc2cf4c3e2e5f
3
- size 27224850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4a89ebc631e3f00654bc78e8210d0748f57712511b4d60134accccf28302f5
3
+ size 27225040
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 sha256:8c7ba23d82397327ac89e4194b35cea8aacace2a0a9f246007b27dbc193fa6bb
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447c81d908d0deeaea319353e9c495548308cec99dce701cd468e9f1a6fb1cbe
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:899edf44ebc29895879109f79cbcc878aca75b4fdf65f1438fc91251d8a121f3
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5985644e7c367c16955765f0f5509e34a8e33df63aef5fde4f047c897479d6f8
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- - OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
  - Python: 3.9.16
3
  - Stable-Baselines3: 1.8.0
4
- - PyTorch: 2.0.0+cu118
5
  - GPU Enabled: True
6
- - Numpy: 1.22.4
7
  - Gym: 0.21.0
 
1
+ - OS: Linux-5.15.0-52-generic-x86_64-with-glibc2.31 # 58~20.04.1-Ubuntu SMP Thu Oct 13 13:09:46 UTC 2022
2
  - Python: 3.9.16
3
  - Stable-Baselines3: 1.8.0
4
+ - PyTorch: 2.0.0+cu117
5
  - GPU Enabled: True
6
+ - Numpy: 1.24.3
7
  - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b1a51a9db11a6602a9d2f7af28f353df8ee165ad29be2cb047bcd7de949e522
3
- size 272881
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:905a2a8aff64411ba8524f0d00233b33e0487224663e59197470908c73ab2d2e
3
+ size 185027
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-24T15:09:47.969875"}
 
1
+ {"mean_reward": 642.5, "std_reward": 254.36440395621398, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-25T09:08:44.010353"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17a41ac36c1ea91768cc9edf02783a0ceb7cca10540623ebdad3c78d8bf1586b
3
- size 45820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733ee9f1836932ecdacb838fcb92a69a299984f917b119551a0340a23f9ac100
3
+ size 261866