Hugging Face's logo

Tommi
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Tommi commited on
Commit
d47a4c5
·
verified ·
1 Parent(s): 7b658f6

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +5 -3
  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. 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: 268.50 +/- 78.17
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 32),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 100000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 691.50 +/- 233.57
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yaml
6
  - - device
7
  - auto
8
  - - env
@@ -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
- - 1972458656
60
  - - storage
61
  - null
62
  - - study_name
@@ -67,6 +67,8 @@
67
  - false
68
  - - trained_agent
69
  - ''
 
 
70
  - - truncate_last_trajectory
71
  - true
72
  - - uuid
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - dqn.yml
6
  - - device
7
  - auto
8
  - - env
 
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
+ - logs/
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 574385412
60
  - - storage
61
  - null
62
  - - study_name
 
67
  - false
68
  - - trained_agent
69
  - ''
70
+ - - trial_id
71
+ - null
72
  - - truncate_last_trajectory
73
  - true
74
  - - uuid
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:9fbe81d5d5eeb8611129f69716bd200a14f44429681e230ccb1eb99ff2e4db92
3
- size 13715966
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61540cd6d4da45f309a150bcdfded7d034ac360e8e2af306ee74b999bd6afa5d
3
+ size 27221651
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.6.0a2
 
1
+ 2.6.0
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 sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc9be1419452c38e33c6c639c7e33dfd08ae9fb2e52908040fb99458e9ca832
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3866714963ba1fd5b89b78200d5dd1db44afa1d7142d6207f11d05d03bcd007e
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfa6ce7f1faeea0e9b563b8f39d4b0de6b820636bb48462d12ee344b95c6e99
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: 3.11.11
3
- - Stable-Baselines3: 2.6.0a2
4
  - PyTorch: 2.6.0+cu124
5
  - GPU Enabled: True
6
- - Numpy: 1.26.4
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.1.1
9
  - OpenAI Gym: 0.25.2
 
1
+ - OS: Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025
2
+ - Python: 3.11.12
3
+ - Stable-Baselines3: 2.6.0
4
  - PyTorch: 2.6.0+cu124
5
  - GPU Enabled: True
6
+ - Numpy: 2.0.2
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.1.1
9
  - OpenAI Gym: 0.25.2
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-17T08:31:32.688700"}
 
1
+ {"mean_reward": 691.5, "std_reward": 233.57065312234755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-18T09:56:09.714288"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a32cb60e47a7220aee02497f3cfe07f1baf07ac414b9258bb3abc9fd4245771f
3
- size 5724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec2b495bda42f9ce1559729e6d3899ba15551f3798ae949a5ae311c3822b137
3
+ size 36185