Hugging Face's logo

yp-learn
/
drl-course-unit3

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Xmaster6y commited on
Commit
49bebe0
·
verified ·
1 Parent(s): 8628daf

Initial commit

Browse files
Files changed (10) 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 +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. results.json +1 -1
  10. 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: 293.50 +/- 107.26
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', 1000000.0),
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: 114.50 +/- 68.72
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 500000.0),
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
- - 804761859
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1063085839
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
+ - 500000.0
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:a77627cc08f2917b9105f77ceb7172bd7893890eecc37157fdc9e7713f2f05ce
3
- size 27221025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd78b69140b0b9aff85659c0c4838b714927de27226f4082f4f5882c0055642d
3
+ size 27220524
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 sha256:2a4770cf0e6df0ea21e343b1830719f04572a50bdb08830cb17eeb716b16e660
3
- size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96676c4c3881c941513ed5720a590bfb88232535b2b205572a5f2d886e53df09
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c34af8767a6190379d710166ac54f9496664a07983efb6a327ea001e074935a
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d4257333518fe7d17fe37f6c1e72e7c103a81da13fca9a4666dc9fc26f67fc
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.11.11
3
  - Stable-Baselines3: 2.4.1
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: 3.11.11
3
  - Stable-Baselines3: 2.4.1
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": 293.5, "std_reward": 107.26252840577645, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-22T12:03:48.787222"}
 
1
+ {"mean_reward": 114.5, "std_reward": 68.71862920635131, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-22T15:06:34.997624"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c44987b4b5029ed5163534596366f00795ac35d24e0bf03cb7784218e7bdc77
3
- size 16821
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a021f42028d0c0915c970bb57f3f7153da361ef8dc9645881b844a7f571a2b9
3
+ size 12333