Hugging Face's logo

jerryvc
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
jerryvc commited on
Commit
1f4656b
•
1 Parent(s): 62fb667

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 +1 -1
  9. replay.mp4 +0 -0
  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: 516.50 +/- 200.41
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: 927.50 +/- 472.12
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
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1241329185
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 4047298367
60
  - - storage
61
  - null
62
  - - 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 sha256:2400b19f25adeddf3f76498905aad7fc3873ba637d2126abb0b7110aa2655976
3
- size 27220728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e4a580258c5d15e78e7c9981611c1215523e1bfb52956e76bd0476e0192710
3
+ size 27220744
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 sha256:07c4dbaee1572834c4ece5db2976805caf7d73136a4013a98efb9f7a9d2ecd18
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23134d4f7746bf96bb1f4f2855d20d7b0ca80ac4488e75431adf14ed1da0f352
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4b5dd0e3b368d5c57e2640230a9d5697972034396a320f634b54ec12dc390bd
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383adf583a23fc1649bd4f45f08f8614de8537a9725e7ff8524d5a71fedd663a
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,4 +1,4 @@
1
- - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a7
4
  - PyTorch: 2.4.1+cu121
 
1
+ - OS: Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0a7
4
  - PyTorch: 2.4.1+cu121
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 516.5, "std_reward": 200.41269919842904, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-06T04:00:34.530630"}
 
1
+ {"mean_reward": 927.5, "std_reward": 472.11889392397757, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-06T14:35:41.613569"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c1535c8b015d7f38090e647f6d852bb47e6fa54b8afa909804bb5df389e27c1
3
- size 38828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8452d90c7729b74655f0b0eb4273cb550cfdcce6af9c85b05d470e8da3aa7e28
3
+ size 273858