Hugging Face's logo

moisesrobles04
/
SpaceInvader-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
moisesrobles04 commited on
Commit
ec9ad3a
·
1 Parent(s): 701afee

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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 +1 -1
  8. replay.mp4 +2 -2
  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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 64),
66
- ('buffer_size', 150000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 64),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
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: 223.50 +/- 89.39
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 64),
66
+ ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 800000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 369493144
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 122165829
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
- - 150000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 800000.0
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 sha256:419a4382c59e44ff932e98aacd39f6424961723e7dbab73fdcf6f580de989a94
3
- size 13713323
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47db1150cdd059039a22520123f465ec108ba6a4cbe7fad0e9d07d4e187c2ad3
3
+ size 27218381
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 sha256:0deb940c86ab5538de5b7bd48f2a3305a3491099536c85fbff2bf1588b36f07a
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19263a327fe6a9b664437c52cf77407c7a33078bea1cccf04d6ae8ba39a7621
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4c9651c211da630781e9278acdc0bdcccf029f93947f97b9c98645cbf8296bd
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a43008a3c7cb53adef164e80bbd0424b8a2d480e874101e74cd3b8451ead551
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e402fa68302f9262ebfd7be784ce6ff6785b68f25d4aa3a86e2c515a7bbb11
3
- size 242628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c22dea565ea383fff3bc509d502adf0a52a1b963f654e167c3ac3df4c52175
3
+ size 278865
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-19T17:49:56.047782"}
 
1
+ {"mean_reward": 223.5, "std_reward": 89.38819832617726, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T18:25:43.430477"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a21931846020cf1092dd2a82cf21a0503d6301c20a43cdc3ca5b40e21e64614
3
- size 5892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3494e7d91cb5b40bef174b8d76a6fd17e2e50ccb7e4d67b256cdb3e2b3d346
3
+ size 33730