Hugging Face's logo

antonioricciardi
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
antonioricciardi commited on
Commit
6b74567
•
1 Parent(s): b524f1e

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 +4 -4
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 329.00 +/- 156.36
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
@@ -60,7 +60,7 @@ OrderedDict([('batch_size', 32),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
  ('learning_starts', 100000),
63
- ('n_timesteps', 1000000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 207.00 +/- 100.40
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
  ('learning_starts', 100000),
63
+ ('n_timesteps', 200000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -50,7 +50,7 @@
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 2595429044
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 401507521
54
  - - storage
55
  - null
56
  - - 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
  - true
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 200000.0
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b73e2fa0af9760022ba46c3f0e8fcb9f8ca2d74548a25db852fba5b51f49727
3
- size 27221757
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6539e9bd0a352df3bd0b991b32d3bf775a477c34adf00123351277b72aeb974
3
+ size 27221976
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 sha256:2bc52e626de9e6e1b015110595e692a93a32cf95fd001b8abc16a7c90c799c3f
3
  size 13502889
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8029e963ec036052eb18fa4488baab47e15a177901536212a6e52f6fe3d90af
3
  size 13502889
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80efd5f2f4991ead1ad767aa21e2b84592f9353e37427abc589f07657e56f9a7
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa929973de20b22758e730aad4256aab0d14eb54831f437fe5c1867a7b7b7029
3
  size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
2
- Python: 3.7.13
3
  Stable-Baselines3: 1.5.1a8
4
- PyTorch: 1.11.0+cu113
5
  GPU Enabled: False
6
- Numpy: 1.21.6
7
  Gym: 0.21.0
 
1
+ OS: macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000
2
+ Python: 3.8.9
3
  Stable-Baselines3: 1.5.1a8
4
+ PyTorch: 1.11.0
5
  GPU Enabled: False
6
+ Numpy: 1.22.4
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58b477252641d3c419f08c8c40b14f67983dc94eabadcfb1569cae88c4b6c83
3
- size 239246
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de771f3b9d8bc6a0b113fffa5321f18a60d1e3f2a1fd168154768c1690c1773b
3
+ size 241718
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 156.36176003102548, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-18T14:52:18.825069"}
 
1
+ {"mean_reward": 207.0, "std_reward": 100.40418317978589, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-18T20:04:57.639559"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37346666405454479730ae1354f8c6f5d9c2e3f379f65231a6853696f27cb6e4
3
- size 9052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf541ebfa6b020af5272af52e8dbdfb2f7cfe44fe41e952dc81ddb40f80838f
3
+ size 9538