Hugging Face's logo

ByeByeFlyGuy
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ByeByeFlyGuy commited on
Commit
31229b3
•
1 Parent(s): e300245

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +2 -2
  2. args.yml +3 -3
  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 +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +6 -6
  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: 541.50 +/- 237.23
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', 0.0002),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 617.00 +/- 224.77
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', 1000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -2,9 +2,9 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yaml
6
  - - device
7
- - auto
8
  - - env
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3615725038
58
  - - storage
59
  - null
60
  - - study_name
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - dqn.yml
6
  - - device
7
+ - mps
8
  - - env
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2601710490
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0002
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:a0cf6c079df53646b518578a71f17f5ab95eba320c88c7df2bb62896bd960c10
3
- size 27220788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36010291c8c508e7c3198601c8fd9678b79a6a5eb71642f26540c376a0a8675e
3
+ size 27220277
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:cc7696e84ac6a7803c9c4aecbdd7bb759891071f985f891d2dd1d9dc8101f7f3
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eea15eab537a9eb8473bbba5123cca926945a45fcf4db0e5177e0a02824e4b0
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9703d4456bc3873d1da1718e5cb8f64014d2c83f0651d695bae729e680727d63
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29038d3679b5ea085527c39c71412212363af42a9508008218c872684749f2f
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
  size 864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
3
  size 864
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
- - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.2
4
- - PyTorch: 2.2.1+cu121
5
- - GPU Enabled: True
6
- - Numpy: 1.25.2
7
- - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
 
1
+ - OS: macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:10:42 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T6000
2
+ - Python: 3.9.6
3
  - Stable-Baselines3: 2.3.2
4
+ - PyTorch: 2.3.0
5
+ - GPU Enabled: False
6
+ - Numpy: 1.26.4
7
+ - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf9904e8f300af6c7ede830c9b3d2d2d88e841bf973a89a83609541060a46d3
3
- size 263000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3edc7c91a493b957aa8dd708413687af2d3a80811efa5c6fd3b722a5b64df4e0
3
+ size 227659
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 541.5, "std_reward": 237.23458854054144, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-09T04:32:31.521049"}
 
1
+ {"mean_reward": 617.0, "std_reward": 224.76877007271273, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-09T18:16:01.136036"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96c78d7b1f1250234aff2064ddd31aa82ef632d55f061d9e42e725ef727b6fb
3
- size 34293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7065f18536eb30fa944762a77315f800babf037a8a03ab0d154289eab080bf8f
3
+ size 36761