Hugging Face's logo

ZeyadGamal
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ZeyadGamal commited on
Commit
52d8235
•
1 Parent(s): 705f6c7

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  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. 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: 255.50 +/- 133.28
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,16 +63,16 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 128),
66
- ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
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: 562.50 +/- 146.38
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 128),
66
+ ('buffer_size', 200000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 3000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3817932395
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3827818252
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 128
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 128
4
  - - buffer_size
5
+ - 200000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000000.0
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:f6c7a45d64105b2df03fe3cf40f2b2c51bf25ca5b6cd62fb913d82d9c83bdf46
3
  size 27220245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002ef6583313ebcf53d8efeace9d913d6ef52454f800197d37f80c2b186e2487
3
  size 27220245
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 sha256:38bc004fc198789db295418978d3c73d8ce58efb1c2c57efcc1a0a87c0586486
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7d1799a6fbe878a3fd9829c4b49bb5a08f5e93ccf58a1c3aca05ed84f9ff79
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cb37dced7f4a25a6a80dd377ee86b7167db787555c590de0743f023698d243f
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33cb0552f15d5b6ca15459ff79d2c8ceb977bfdfa44c5a961e75d4063e8e2ec
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a72eb0ae3e32ba6a0edc899786e1353986aef090c2c7de6443f8ba4067e679cc
3
- size 263790
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df8ddbea511bd84810d2917abbcf8193731b4790700e7f3169f30290defd8fc
3
+ size 248296
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 255.5, "std_reward": 133.27509144622636, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-20T17:07:56.617703"}
 
1
+ {"mean_reward": 562.5, "std_reward": 146.3770815394268, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-20T22:31:29.912907"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5918cbce741acb1a41b47fdfa334e87a4f424a228f178bc8d149dca3456b792a
3
- size 38682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a45ff7ef9a026633501c0c5fe3822c8fc4dd541b2d73b22dc7d831d5c22af2
3
+ size 90615