Hugging Face's logo

esperesa
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
esperesa commited on
Commit
ccdf20d
·
1 Parent(s): 70f9006

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +2 -2
  2. args.yml +2 -2
  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 +7 -7
  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: 600.50 +/- 140.79
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: 1124.00 +/- 189.17
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
@@ -20,7 +20,7 @@
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
- - logs/
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3938311393
60
  - - storage
61
  - null
62
  - - study_name
 
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
+ - /home/luyang/logs
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 334622670
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:c6b267edd4f1cfc3c9f65ffc6405a660b6275ea362dba6fd5c7cde570cc68a24
3
- size 27220728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f31e8b4af033c662bd94dccdf6c8e60eaca2e858e242163e28776096a334e90
3
+ size 27221776
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.4.0a7
 
1
+ 2.3.2
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:db6ce4e68e27dd308a9162210230f48e39f12d5a4a70918f5561858638645c93
3
- size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4c2926f26728409481b19f1ede6562098191066e83d9400d3bbfb729fd58af
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a2d9c99d3fca2489e669bf3820cec43f3a8dc2d93787e2ce0d60459ae3d853e
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a772f6f7543493ef07ad1d044ac45f2ebe29601fd84416c907c7694efd56dd1b
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
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: 2.4.0+cu121
5
  - GPU Enabled: True
6
- - Numpy: 1.26.4
7
- - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
- - OpenAI Gym: 0.25.2
 
1
+ - OS: Linux-6.8.0-41-generic-x86_64-with-glibc2.39 # 41-Ubuntu SMP PREEMPT_DYNAMIC Fri Aug 2 20:41:06 UTC 2024
2
+ - Python: 3.11.9
3
+ - Stable-Baselines3: 2.3.2
4
+ - PyTorch: 2.4.1+cu121
5
  - GPU Enabled: True
6
+ - Numpy: 2.1.1
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 sha256:866edf0ff31cb19269d3772db61e9889798e0fee7cfdc86ce875f244f69b6a86
3
- size 210472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d4773ccf89b75620f30d80693532997bdb93df145e260e4f20e9deb830cbe9
3
+ size 213961
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 600.5, "std_reward": 140.79151252827708, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-01T17:41:01.148914"}
 
1
+ {"mean_reward": 1124.0, "std_reward": 189.16659324521336, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-16T02:42:52.180832"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5baf0708a3262ab72f79c5a4f5e8a7e1931c86e629d4ad2f1d3b276774497f4
3
- size 37555
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c80a6b65d04b4e1fe46a3e40bf67fbff4073c1420c80c8065ece8a4552831f
3
+ size 260817