Hugging Face's logo

ezrab
/
dqn-SpaceInvadersNoFrameskip-v4b

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ezrab commited on
Commit
5663ae1
·
verified ·
1 Parent(s): eb694d7

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  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 +2 -2
  8. results.json +1 -1
  9. 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: 535.50 +/- 118.23
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -64,12 +64,12 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
- ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
71
- ('exploration_fraction', 0.2),
72
- ('frame_stack', 2),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 811.50 +/- 320.22
20
  name: mean_reward
21
  verified: false
22
  ---
 
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
+ ('buffer_size', 500000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
71
+ ('exploration_fraction', 0.1),
72
+ ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3607572767
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2389355358
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,15 +2,15 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.2
12
  - - frame_stack
13
- - 2
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 500000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.1
12
  - - frame_stack
13
+ - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:580564f5786abc519c3e8699533e9be8ea65b84a27a67448b17019872e246d63
3
- size 27059203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ca44382db1641fedd90c657143750f00e53915aa336b9671e8803c3ab9a726
3
+ size 27220639
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 sha256:2ef71a72e1c9119540d8c3bd8e9c450571f6eeccc06d21593bb6cf08d29b2829
3
- size 13473404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d5d01387b4b3c086d215a43f3387435c729f02a45cd66474f39c85963e8b114
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a814d84e4c0646dfd7716a399be89dcf2cc2fbc1f7a7a3a1e8ea2f05c518c4b
3
- size 13472602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a631c6e7329fbf5f9913d054a5ea8ff899e6bbc790684c58b69b5ad1e19a65
3
+ size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 535.5, "std_reward": 118.22542027838176, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-06T06:33:30.356995"}
 
1
+ {"mean_reward": 811.5, "std_reward": 320.2190656410077, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-06T18:20:02.260251"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c11a3fd3134ade3066eebbd2a9f0e4a6ddd56ff70b6039d44410364ae5d963
3
- size 40047
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c37ff9a81720f4cc1307ffd9c17f0bbeb320a380b2c4447f1e535d29ba8618
3
+ size 36584