Hugging Face's logo

LeKyks1
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
LeKyks1 commited on
Commit
c38d8b0
•
1 Parent(s): a25835d

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +1 -1
  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. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -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', 16),
66
- ('buffer_size', 1000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 16),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.01),
74
  ('learning_starts', 1000),
75
- ('n_timesteps', 500000),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 500),
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 16),
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', 0.01),
74
  ('learning_starts', 1000),
75
+ ('n_timesteps', 800000),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 500),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 736452160
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2285593421
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 16
4
  - - buffer_size
5
- - 1000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 1000
20
  - - n_timesteps
21
- - 500000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 16
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 1000
20
  - - n_timesteps
21
+ - 800000
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 sha256:3700f3135d477a16e7fa23996c58ae8545e04f81620016102bf8b86ee0bf235e
3
  size 27220130
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcbe27bcefa8a3a6e3a096186c0925514317a1c556d51321fe002b1d7aeb549
3
  size 27220130
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:b3d16f90aa28fb5be9d9631a1a7119ad668809910d7295eec4119762a5aca9ab
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec9d681850ed437c2269552eee4b7ec94e01e96e4fc230ea4a6af487352b315
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3240abcbbbca24655dbbd504ade02454201ce84404a5e4217c47b95bcc77d37f
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd0493bdf7891137a73d9966f54ec6f0889d4578c621c42ff13e1903c77d315
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T18:48:01.505333"}
 
1
+ {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T19:55:41.870417"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a16d9e30ad0abeb5cf3c28c64050a28c3623dec1f8286c1d34cb8842f0a2600
3
- size 20955
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c751eaa1374aa9bac5925f7b526adb63763a88b99b6879ed153d54cff2e7cf62
3
+ size 31635