Hugging Face's logo

EdenYav
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
EdenYav commited on
Commit
188f579
•
1 Parent(s): 12390e8

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  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: 90.50 +/- 51.16
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,16 +62,16 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
- ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 275.50 +/- 83.08
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
+ ('buffer_size', 150000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0005),
74
+ ('learning_starts', 100000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3797466460
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 480977459
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
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
@@ -14,9 +14,9 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
  - 100000.0
22
  - - optimize_memory_usage
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
+ - 150000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0005
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
  - 100000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db89135e6dd26a7c3ec09a70bb7c426ef4047d055f7e6046e7e245dd4a4f4339
3
- size 27224801
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4277292723247c13f8b722525490f494df617d9811152fa98baf3e290f62329
3
+ size 13719746
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 sha256:5fd3e1f595a7d4e1ee15084257910521818c8fdf44dcea9277e6e01ee381c64c
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806804ebabef9eec640330a6472ba384103459468f2ea3a2c8ffde2197d45835
3
+ size 687
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6b7ed668ba626cddacf11db894de9f7647c1a1576f86afca0d0e2942eb505ac
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba1e71f156fbc9f9de3a0153420f114e9759ac99a297e9e95d4892f501b5021
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30e538f92b94c907f5569da67e56b8039edebc5d974039f3468067c777795401
3
- size 258972
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caa6a1f28e357785d754b2769d1539f69db8d8cc9b953475f14f2f15f30761f4
3
+ size 263235
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 90.5, "std_reward": 51.15906566777779, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-08T11:42:42.004942"}
 
1
+ {"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-14T08:40:14.882651"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7ef98e8b8aef95933859b80021be6c9c0b32bb64a5ce9a17fc452b737fae467
3
- size 5183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ac3e09bb9161128c5eb1129748089f2656d6e0866cac809766e43d18f76a25
3
+ size 5798