Hugging Face's logo

debisoft
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
debisoft commited on
Commit
3ca59aa
·
verified ·
1 Parent(s): 86d3e3c

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 +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: 671.00 +/- 204.81
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -64,14 +64,14 @@ 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', 200000),
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),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 263.50 +/- 141.55
20
  name: mean_reward
21
  verified: false
22
  ---
 
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', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 1e-05),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3020163880
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2719719223
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
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 1.0e-05
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:a43bf9e556547f929b1daa63e3eb7062f54bf0c807ff4c85ccf6ef11b73301a0
3
- size 27219633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23abe03056c37d7a85f27aec66bb69f50dffbc66dd2c2551d5edfddb334af517
3
+ size 27219627
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 sha256:5792e711e306ec087efec3a3e49636873cf1a86f70b1c70f297129676a060b7a
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163378d0479fe846bbea75af5e16c3a6284a471e89573882ec152238a2ee0f95
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:980d3415d6b72c3af363047077e416efbff944268c5f9aa8ace221a0d62e8356
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cedc968ac18e4fc1d1b1c2b9ddcb6abc0bcce7c440fd2fefd6d5a9e3bd6a8df
3
  size 13505767
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27de79b1a4a2f208937c18bfb6820867e0b56f379d7d90321dd0c9bf0c874576
3
- size 202606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3b9257439e10c6943122585960fca8eb4859b77abc983f692979c0ff984fa4
3
+ size 254190
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 671.0, "std_reward": 204.81455026437942, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T02:59:34.337278"}
 
1
+ {"mean_reward": 263.5, "std_reward": 141.54592894181027, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T03:38:52.287127"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d5ef3e82d430a47144785d1bd8743bc02ee733a379c85ad0d49b24fad70149
3
- size 35925
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9d3b63072ab00eb3e9b41271a7421ed17a24e6f8e6f873c88b109757a7dd87
3
+ size 42305