Hugging Face's logo

jfelgate
/
dqn-SpaceInvadersNoFrameskip-v10

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
jfelgate commited on
Commit
27b6b69
·
1 Parent(s): d4bfc08

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -5
  2. args.yml +1 -1
  3. config.yml +2 -6
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  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: 102.50 +/- 73.05
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -66,16 +66,14 @@ OrderedDict([('batch_size', 128),
66
  ('buffer_size', 50000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.1),
70
- ('exploration_fraction', 0.25),
71
- ('gamma', 0.99),
72
  ('gradient_steps', -1),
73
  ('learning_rate', 0.00063),
74
  ('learning_starts', 0),
75
  ('n_timesteps', 100000.0),
76
  ('policy', 'CnnPolicy'),
77
  ('policy_kwargs', 'dict(net_arch=[256, 256])'),
78
- ('target_update_interval', 250),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 158.50 +/- 118.70
20
  name: mean_reward
21
  verified: false
22
  ---
 
66
  ('buffer_size', 50000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('gamma', 0.95),
 
 
70
  ('gradient_steps', -1),
71
  ('learning_rate', 0.00063),
72
  ('learning_starts', 0),
73
  ('n_timesteps', 100000.0),
74
  ('policy', 'CnnPolicy'),
75
  ('policy_kwargs', 'dict(net_arch=[256, 256])'),
76
+ ('target_update_interval', 100),
77
  ('train_freq', 4),
78
  ('normalize', False)])
79
  ```
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2295009967
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1256430113
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -5,12 +5,8 @@
5
  - 50000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
- - - exploration_final_eps
9
- - 0.1
10
- - - exploration_fraction
11
- - 0.25
12
  - - gamma
13
- - 0.99
14
  - - gradient_steps
15
  - -1
16
  - - learning_rate
@@ -24,6 +20,6 @@
24
  - - policy_kwargs
25
  - dict(net_arch=[256, 256])
26
  - - target_update_interval
27
- - 250
28
  - - train_freq
29
  - 4
 
5
  - 50000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
 
 
 
 
8
  - - gamma
9
+ - 0.95
10
  - - gradient_steps
11
  - -1
12
  - - learning_rate
 
20
  - - policy_kwargs
21
  - dict(net_arch=[256, 256])
22
  - - target_update_interval
23
+ - 100
24
  - - train_freq
25
  - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea3a66c3bccb180203c0734f71f687ccc0c9d980d8d1a93cbd28755450f7cd10
3
- size 30113655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66cd778412b1d0ad8587b32918cf4dfa2f33718944f2dc2a75124355f9fe4813
3
+ size 30113656
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 sha256:2381e6426f404c41e337f0d2b9115343ec7f4b3436a53ad8eb9cd801bee5f089
3
  size 15025112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b823f49717325b1122d6cc4de199133f0aae7ef301feb743fb53160bd8e9a9d4
3
  size 15025112
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5080588f52c98bfd7ef2967cf2e27b4d7016dcc9b6582842f6cc4b710da7181e
3
  size 15023810
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c323947627f5faa0c3a1d90aa5219ea0491e9655630b154638c1473ec91158b3
3
  size 15023810
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5d5175704e77de5a980f11351b5af0513e61094b8812c11a15ca1264c36f375
3
- size 265515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58774d71cd06b47134d8b232dea82f40a2029e6adbd9fbba03d256e079eeabdb
3
+ size 258119
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 102.5, "std_reward": 73.04964065620035, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-10-30T04:36:09.013001"}
 
1
+ {"mean_reward": 158.5, "std_reward": 118.70235886451457, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-10-30T04:54:18.799653"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:007ee147aa2853d557fcd438b1fcb1b758818dd45d3e512ec08254c0cc5e14fb
3
- size 5467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af32a836ad167e551555618b057a8e5aff3df8b3afdc20f10e552e70aea1eea5
3
+ size 5316