Hugging Face's logo

malibanekg
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
malibanekg commited on
Commit
7450a5f
•
1 Parent(s): 2ed1bdd

Initial commit

Browse files
Files changed (12) 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/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +4 -4
  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: 605.50 +/- 94.96
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 998.50 +/- 347.35
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2276898160
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3903964739
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:603ee326be6671dc9f51d7c86e120293a8ec0a8d8147da90efafee8fe456c7de
3
- size 27224807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790ff7b275c05fda9c15c7c80e03820db665b07c45add75feb65a23f375d5c20
3
+ size 27222549
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.8.0a2
 
1
+ 1.7.0
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 sha256:47eb9e09e6e6a92909b2d7fb5f7c8541e5799ab8821369989923e62efa4cbaf6
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c81a6560d8fdfa92efcee96ae1e223bbc58255c28550f4d3a9857ff55bad0e
3
+ size 13503145
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90b1b44cffca070937afca6fbf42087a5d3203e2f7de36facac32ccf85655a43
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2508f8227cef896f8447b67d902cff6b080163183cc2442ffcb6a8113ca5b807
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- - OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
- - Python: 3.8.10
3
- - Stable-Baselines3: 1.8.0a2
4
- - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.21.6
7
  - Gym: 0.21.0
 
1
+ - OS: Linux-5.4.0-51-generic-x86_64-with-Ubuntu-18.04-bionic # 56~18.04.1-Ubuntu SMP Tue Oct 6 09:47:18 UTC 2020
2
+ - Python: 3.7.5
3
+ - Stable-Baselines3: 1.7.0
4
+ - PyTorch: 1.11.0+cu102
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 sha256:4f427017611244518ded506b03eca41185f8963fb566a987b5ea89de9896bfe4
3
- size 225359
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9b5908c97010020ad957ed1131c9c751de58ba34cdfbebbbe4c8a2e6a7b9f7
3
+ size 196031
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 605.5, "std_reward": 94.95920176581099, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-26T23:18:33.791460"}
 
1
+ {"mean_reward": 998.5, "std_reward": 347.3474485295667, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-04T23:27:35.358524"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07a1bb5f26c276a73f3f394f59475a899a6aa6baae53b97a0fce5c88289b1c10
3
- size 37758
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6e1c2939023dba90e06ed4e5849f5beadff9a99154132f54624b38dc9267b4
3
+ size 269088