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
eb694d7
·
verified ·
1 Parent(s): 6d830b9

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  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. 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: 567.50 +/- 188.89
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -68,7 +68,7 @@ OrderedDict([('batch_size', 32),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
71
- ('exploration_fraction', 0.1),
72
  ('frame_stack', 2),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 535.50 +/- 118.23
20
  name: mean_reward
21
  verified: false
22
  ---
 
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),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 294487475
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3607572767
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 2
14
  - - gradient_steps
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
  - 2
14
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89805538378bfd6231685da09ffd70dbc5b182301970e27663426c003e414a6b
3
  size 27059203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:580564f5786abc519c3e8699533e9be8ea65b84a27a67448b17019872e246d63
3
  size 27059203
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 sha256:9cb841fe0c36347a2eedc4f43926da2eacc0d14672682eaf03c249e487ae395d
3
  size 13473404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef71a72e1c9119540d8c3bd8e9c450571f6eeccc06d21593bb6cf08d29b2829
3
  size 13473404
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dccb47df4a651f21945a5a26d4ea9fe465dc81d0a0f60dd6bc90de28146314ae
3
  size 13472602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a814d84e4c0646dfd7716a399be89dcf2cc2fbc1f7a7a3a1e8ea2f05c518c4b
3
  size 13472602
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 567.5, "std_reward": 188.8948119986359, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-06T05:31:51.276192"}
 
1
+ {"mean_reward": 535.5, "std_reward": 118.22542027838176, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-06T06:33:30.356995"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c370afc8f4d6850a784508afd4c4f2023787bb6d027deba63d8d70477225c544
3
- size 41897
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c11a3fd3134ade3066eebbd2a9f0e4a6ddd56ff70b6039d44410364ae5d963
3
+ size 40047