RamonAnkersmit commited on
Commit
6fc114a
·
1 Parent(s): 3d59e7b

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 374.00 +/- 214.89
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,15 +57,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('batch_size', 16),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
- ('exploration_fraction', 0.1),
66
- ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 0.001),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 527.00 +/- 220.46
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 32),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
+ ('exploration_fraction', 0.025),
66
+ ('frame_stack', 3),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1069349440
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2989382765
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 16
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -8,13 +8,13 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
- - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.025
12
  - - frame_stack
13
+ - 3
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
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 sha256:0ceaa737a7114cbb5f1191c306bbed863daa9ae826b938d5a5b3846cb59f4638
3
- size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fe42182f075450c7abd138b7c7486bf603bddb8be5cb0ff731d0e9ba1590aa
3
+ size 27144084
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.6.2
 
1
+ 1.7.0a10
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 sha256:375b860e110b7be2f9da38da3f0fe7bcc503a5d007cf2e7ae753dcaf3cf8ec9f
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0127f09bfebbfab6e0e95edf5f429d07a073f85d68dcaa3edfd9a8f686c9e6
3
+ size 13489355
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de3b4f8a1ec2a36d84f01ff7b9e0b6fbfb52154b65ccf7b0fcc1c0be80c200e3
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1168910a71d949e5cdb418d34d1df1a8139a74c55208d9954845dfe9015d0b
3
+ size 13488553
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
1
  OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
- Stable-Baselines3: 1.6.2
4
  PyTorch: 1.13.0+cu116
5
  GPU Enabled: True
6
  Numpy: 1.21.6
 
1
  OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
+ Stable-Baselines3: 1.7.0a10
4
  PyTorch: 1.13.0+cu116
5
  GPU Enabled: True
6
  Numpy: 1.21.6
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b231c3e33922a65189db4066e7414df0b5a66d5fa35017253dc63dd0d43b457
3
- size 233415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b8dcd7b098e3d17dd6c7206b1795abba5236bd96bcdd4b089c6f3fd51a9d9b
3
+ size 206858
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 374.0, "std_reward": 214.89299662855464, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-19T22:14:07.643212"}
 
1
+ {"mean_reward": 527.0, "std_reward": 220.45634488487738, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T16:43:44.510264"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25471be8f6630682b10afbad6ed662f144cdf126f6abdb4bed4cb6d88dc2fea9
3
- size 40539
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34df2d496212e4d9c3c0b3170fa533b4177dda3d0a8e74b530ca10c28af7129
3
+ size 38596