Hugging Face's logo

pmmanalo
/
dqn-BeamRiderNoFrameskip-v4-2

Reinforcement Learning
stable-baselines3
BeamRiderNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
pmmanalo commited on
Commit
a7ec832
•
1 Parent(s): 7ea707f

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-BeamRiderNoFrameskip-v4.zip +2 -2
  5. dqn-BeamRiderNoFrameskip-v4/data +0 -0
  6. dqn-BeamRiderNoFrameskip-v4/policy.pth +2 -2
  7. dqn-BeamRiderNoFrameskip-v4/system_info.txt +1 -1
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: BeamRiderNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 568.80 +/- 126.46
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', 200000),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: BeamRiderNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 13.20 +/- 20.16
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 20000),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 161184070
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2411528922
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 20000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-BeamRiderNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ad6035bf71e95420b7a0cae970980ef24176a7d2c0b5b0d189bd551c02b489b
3
- size 13724476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2863b0b1bca2725dcf602b845a9e4b0ed108b484462f6243940ea67c6c7a7a2c
3
+ size 13724115
dqn-BeamRiderNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-BeamRiderNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2509be3e061e008e46f738fef59f00b633dbf652a3225cab15ebfd2e332c12f
3
- size 13517658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b70fbe343202aaea13d58027061705b3b9e1ee301fe389d912f42366096239
3
+ size 13517466
dqn-BeamRiderNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0
4
  - PyTorch: 2.5.1+cu121
5
- - GPU Enabled: True
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 3.1.0
8
  - Gymnasium: 1.0.0
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.4.0
4
  - PyTorch: 2.5.1+cu121
5
+ - GPU Enabled: False
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 3.1.0
8
  - Gymnasium: 1.0.0
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 568.8, "std_reward": 126.4632753015673, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-12T07:12:28.270149"}
 
1
+ {"mean_reward": 13.2, "std_reward": 20.163333057805698, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-12T07:15:48.123436"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa95a265d96e1e24acaf6f3223e39dbd3536511ea66ccd06895b73824f94181
3
- size 591
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d536526182c8782387bc98327c91d08f5b1180b548a556aef358b9d5eaa9fae4
3
+ size 504