Hugging Face's logo

Ale902
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Ale902 commited on
Commit
ea43c7e
·
verified ·
1 Parent(s): 8cc82d8

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +2 -2
  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: 218.50 +/- 65.69
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,8 +63,8 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 64),
67
- ('buffer_size', 250000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 64),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 170000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 745.00 +/- 273.87
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
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),
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -20,7 +20,7 @@
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
- - logs/
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 463663602
60
  - - storage
61
  - null
62
  - - study_name
 
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
+ - logs
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 791084428
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
- - 250000
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
- - 170000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:6ca7e6a43fa0b901213b164b339c4dc54508741903991e78cbd69666a7f7c87a
3
- size 27218403
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3244d21e9ee797c84f7015e245c1f30e834a02e5dbae810e61e6a2ef807d31d6
3
+ size 27218408
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:d8b95a83c378d17d3e840438785f9ad4d3092b66a01167e07cfa9e2e56011552
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f06cb14f82388d4f8dfb3a49ea3bed40a0c75c43353fc1c409262e38e02b74
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6db490c8b2cd077018e6c81096aa419a8aed371fb46267615d4621d61b3e14b1
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1a00101171b16017a55e443330313616c69b446817085279474d711e0ee910
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 218.5, "std_reward": 65.69056248807739, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-20T16:26:50.383411"}
 
1
+ {"mean_reward": 745.0, "std_reward": 273.87040730973473, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-23T15:17:35.844228"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d919a768479ef9d6f651ced9f866bd220f4544e750f10d41a169f26ab69f3293
3
- size 8350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128dc933eaf2a21558c9777eb633b142a3a853c193e7662c355a1b7b28827a07
3
+ size 35748