Hugging Face's logo

andyv237
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
andyv237 commited on
Commit
7e1dc65
·
verified ·
1 Parent(s): 51cb61c

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 +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: 137.00 +/- 58.62
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,14 +67,14 @@ OrderedDict([('batch_size', 512),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
- ('exploration_final_eps', 0.05),
71
- ('exploration_fraction', 0.3),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 4),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 20000),
76
  ('n_envs', 4),
77
- ('n_timesteps', 200000.0),
78
  ('optimize_memory_usage', False),
79
  ('policy', 'CnnPolicy'),
80
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 244.50 +/- 92.69
20
  name: mean_reward
21
  verified: false
22
  ---
 
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', 4),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 20000),
76
  ('n_envs', 4),
77
+ ('n_timesteps', 1000000.0),
78
  ('optimize_memory_usage', False),
79
  ('policy', 'CnnPolicy'),
80
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2851671363
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3565632226
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -6,9 +6,9 @@
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.05
10
  - - exploration_fraction
11
- - 0.3
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -20,7 +20,7 @@
20
  - - n_envs
21
  - 4
22
  - - n_timesteps
23
- - 200000.0
24
  - - optimize_memory_usage
25
  - false
26
  - - policy
 
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
 
20
  - - n_envs
21
  - 4
22
  - - n_timesteps
23
+ - 1000000.0
24
  - - optimize_memory_usage
25
  - false
26
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54186496db5048b77c75cc40cf80c3ae707fd93092361a4b43cac1cf3d71592a
3
- size 27331317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969f9b55d9a850a883e7661fa449e089244e25ebfb55c3bde99696ae59a93edf
3
+ size 27331337
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 sha256:6cd42c7c260167e1ab19da554afede6709d48ed21e26f27b09350db982e27f0a
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67815464e8ca0da357fd518c214d2f6768433ec080bd91bb02a6200b24985787
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37ddff56a36f542349ead8c79ba73c0cb55f31c3320e10a9b82f3ab746dbcc1d
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca09921578da14dd2172d39461b3b66925cb2c624b3093bd8ccc48848667e23
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 137.0, "std_reward": 58.61740355901138, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T16:48:53.511343"}
 
1
+ {"mean_reward": 244.5, "std_reward": 92.69439033727986, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T16:51:14.660279"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eef8b19a357041ff80ef664cd1cb955996e43ae9e3c83a4b1d414f3bb33077d5
3
- size 10154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11ae207d6252bf0be366268d1b4813cc3ad944c6867223eaa855604882e7dbac
3
+ size 14110