Hugging Face's logo

jackhhhh
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
jackhhhh commited on
Commit
e3f1a2a
·
1 Parent(s): 53c6182

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +4 -3
  2. args.yml +1 -1
  3. config.yml +4 -2
  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 +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  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: 14.50 +/- 12.34
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,10 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.1),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000),
 
76
  ('policy', 'CnnPolicy'),
77
  ('target_update_interval', 1000),
78
  ('train_freq', 4),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 274.50 +/- 31.50
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', 100000.0),
76
+ ('optimize_memory_usage', True),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
  ('train_freq', 4),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3015455802
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2818137750
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,13 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.1
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000
 
 
22
  - - policy
23
  - CnnPolicy
24
  - - target_update_interval
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 100000.0
22
+ - - optimize_memory_usage
23
+ - true
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:031c938b5cbcdbfa2bb7f36529457e96a9cbb8bb720ba9a02bec2d1b0bb64175
3
- size 13719756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6844dacd9029f6bfc1d38ff1c6b68e6b6c39f7c6010367f403ed9a4dcb9fd0
3
+ size 13719564
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 sha256:8e31aa4350c628f92c962d8c57ac16d132b573d801008f0036bfbb6175edb35a
3
  size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
3
  size 687
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65d2448aa0a13c32aea0acd041dc6ae267d8057d78491b8b912e8b8b19a15deb
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe62a0636b913c5a20ca4985f54da0123f303351cdde03758022b6f0c7c466b
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,6 +2,6 @@
2
  - Python: 3.9.16
3
  - Stable-Baselines3: 1.8.0a9
4
  - PyTorch: 1.13.1+cu116
5
- - GPU Enabled: True
6
  - Numpy: 1.22.4
7
  - Gym: 0.21.0
 
2
  - Python: 3.9.16
3
  - Stable-Baselines3: 1.8.0a9
4
  - PyTorch: 1.13.1+cu116
5
+ - GPU Enabled: False
6
  - Numpy: 1.22.4
7
  - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fed103c47817f3f94ef4564da11c292e2891460f38d04aed7c8ce7eca6e1ea9
3
- size 275554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba2ab7031f7061f065c3d5bc1de3dcfb9536d40b9bccd2413c48c7909f59ea3
3
+ size 261744
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 14.5, "std_reward": 12.338962679253067, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-18T10:59:46.963958"}
 
1
+ {"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-19T12:20:09.510728"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff5da9a2c2076892e1ec426bf5b9bc2df48b98daf8d939d50b6e3d58de42c31e
3
- size 5756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af51f3c988425dc4ceccf1e398161186a289b986c30c1f5c846bd14399871101
3
+ size 5909