Hugging Face's logo

numan966
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
numan966 commited on
Commit
d9b0b85
·
1 Parent(s): 1693e9d

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 +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: 275.50 +/- 83.08
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,7 +57,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('batch_size', 32),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -65,7 +65,7 @@ OrderedDict([('batch_size', 32),
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 0.001),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 597.50 +/- 179.60
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 64),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1505147591
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2521012230
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e23f4801effdbe36f64bb397a3145878979e2ce7cc742fec48465b7506987798
3
  size 27224794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fb019b22b2e82066491d84c3834b3536382725270d898ed8e38dab6fa5a9e1
3
  size 27224794
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 sha256:2391d56769955c866b7691f38ec74abf6a653120341125ea0fbc2cdd6e2e0ad7
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c0ff4c2e47499742e183acc4985c7009f6cd98b73b84c14032faaecacbba15
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:aa0609c3d1f7db5b19d1e8b458e5959c598166e429c96ee2fe12d9e21f70759e
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52773f6ba5c4444a82bf80cc272f9f319a469f6e2074ba92119ae3b19752774e
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5f67034dcd179b8b2703be039b496e01d8225cc1ff89761db3984f375d8aeb7
3
- size 263235
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1530be5f0b2d2e1e5373fd65d8f51e1555c4f75fc71270fb66a0f70eb512298b
3
+ size 180568
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-30T21:14:54.289079"}
 
1
+ {"mean_reward": 597.5, "std_reward": 179.6002505566181, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T15:28:54.613923"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f68e44910b4cc4e68d739214e6dd25d80d1bbd577b5b041de1061cf3348726
3
- size 40654
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7abbaecb3220e218c43bc8edf81b7f9edc70b7d5bf5d0a0ad28ffcae3db0b1e
3
+ size 36669