Hugging Face's logo

zlicastro
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
zlicastro commited on
Commit
e7981af
•
1 Parent(s): ddf2098

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +2 -2
  3. config.yml +2 -2
  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. 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: 706.00 +/- 225.46
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -58,7 +58,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 64),
61
- ('buffer_size', 150000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 64),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 582.00 +/- 181.28
20
  name: mean_reward
21
  verified: false
22
  ---
 
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 64),
61
+ ('buffer_size', 200000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 2000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 239237139
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +64,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - /content/rl-baselines3-zoo/logs/dqn/SpaceInvadersNoFrameskip-v4_2/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 453092863
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - /content/rl-baselines3-zoo/logs/dqn/SpaceInvadersNoFrameskip-v4_3/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
- - 150000
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
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
+ - 200000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
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 sha256:0c544a5ac69fd3b0fdbca21f133b582bf0b966b49e44442e6b804b527c20150a
3
  size 27224795
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79fae8da414e5666072d13ee41f0b72005fcc39d4c05f24835c67c81757689e
3
  size 27224795
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 sha256:7d3f32e7b9ed4011680af65e991d1d8a5f74aa62cda806883db5f2c5049e8417
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3e1c0a03458ac5fc2f8b3fbd5ffe8c345c67cd4adece770d28b649fe119fd6
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25b6b2486cc9ce767b0c4cac4effbde3e0e5049bede0404b9adbe97e8f7bb1a2
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3e51a5af85fb736b363c1a11c8f27dddd4506dd45e4fb3255783b62b385a3c
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92352d0b38c32482f827fe6942df24c942aa412a80982ab4f9d647bdcd025260
3
- size 217474
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe0f60bb212db8a93e6cce664dc2cf8796a3d8fee4b9dbd39b0505acdd98a19
3
+ size 211671
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 706.0, "std_reward": 225.4639660788393, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T00:07:48.036019"}
 
1
+ {"mean_reward": 582.0, "std_reward": 181.27603261324978, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T02:56:13.720602"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3d73479d1f783fd66c154e62cb2364a77ff9ae0bb8f2440a5c5ff364888c5a5
3
- size 28289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a15662ca2371a926ab3942f6694bcf3ed2f94aa73f5abb05302dfee72627ef3
3
+ size 53922