Hugging Face's logo

yunk3r
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
yunk3r commited on
Commit
65dc101
·
verified ·
1 Parent(s): 2aa7146

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: 1059.50 +/- 489.28
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', 32),
66
- ('buffer_size', 200000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 2000000.0),
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: 719.00 +/- 257.16
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 220000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 2500000.0),
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
- - 3606913648
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1308828685
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 200000
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
- - 2000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 220000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2500000.0
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 sha256:1d77e47a2a7379797367fa344648bf74f4086ea4fc3f25085f44379f054b1266
3
  size 27220313
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd5ea6b13eb149bc93c0392ac845183ce76be2f6779ef8f1b572c510fd18d46
3
  size 27220313
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 sha256:348d59de91d1a2b1936f31b76a04886ecabbbecd017764c08d6d2adaa1372cf3
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff5f7f47b1d3ac0aa7ce8e9159e870325008d891c74a37a004809e87f36b0fe
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32d0a9918c41da75237895e2396645ae33b44cf7755c09ba0be78d6d7e9276a0
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05d650c2619d31cc39faf4e6cdec2ca320774c6beff17def44cd4c3ad51620b
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50d0d5e7c4d495ddb0717b2aed25352e4da08d4d907cb9b447c6113640b95b
3
- size 215490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5305fcc4e2a727a36c050813daa553a56fa2e6ef4dd2ee80fd95e20eed76e447
3
+ size 222897
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 1059.5, "std_reward": 489.27727312843786, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-07T07:54:42.189560"}
 
1
+ {"mean_reward": 719.0, "std_reward": 257.1555949226071, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-07T12:41:37.390967"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a91f7fbe9bd2740e0e6e9a79b16ac05094868b60028f456d53b6d0713e1c4733
3
- size 60231
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc3487690d1fbd841614571ada06c8402db306c54b953bccdaa9b55487e46df
3
+ size 74208