Hugging Face's logo

Agog
/
SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Agog commited on
Commit
cc20e32
·
unverified ·
1 Parent(s): 850b749

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +6 -6
  2. args.yml +1 -1
  3. config.yml +5 -5
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 217.00 +/- 79.69
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,8 +62,8 @@ 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', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -71,11 +71,11 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
- ('target_update_interval', 500),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 677.00 +/- 93.65
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 8),
66
+ ('buffer_size', 50000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
+ ('learning_starts', 50000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
+ ('target_update_interval', 1000),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 19003863
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3219609418
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
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -16,14 +16,14 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - 500
28
  - - train_freq
29
  - 4
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 8
4
  - - buffer_size
5
+ - 50000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 50000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
+ - 1000
28
  - - train_freq
29
  - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ac2bcfa7979674112e55af05f2ba1df3b35eafa9642a64e3ef9af19222c2142
3
- size 27224807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48de4e4917277fbdd4014950ff5648328d72731cff83e66f6c3a4224697e16f1
3
+ size 27225416
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.7.0a12
 
1
+ 1.7.0
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 sha256:1fe68704a9a650231eb0e86f8e4b314bc629d2e099e0b3729337f3801da01f09
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf0714b8b9d5a3d5a5ed10b72310b15e5904d96db1cf9c3bb4fe226676d2150
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70563d281c01e7b9bc048fc28e7ace20c3986f4f91cb63af973d8ea12dd1397a
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f132c10b0025fda4eaac15ad8d3c3c90d5c6c637de7145c6cef87913d25964e
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- - OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
- - Python: 3.8.16
3
- - Stable-Baselines3: 1.7.0a12
4
- - PyTorch: 1.13.0+cu116
5
  - GPU Enabled: True
6
- - Numpy: 1.21.6
7
  - Gym: 0.21.0
 
1
+ - OS: Linux-5.15.0-56-generic-x86_64-with-glibc2.31 # 62~20.04.1-Ubuntu SMP Tue Nov 22 21:24:20 UTC 2022
2
+ - Python: 3.10.9
3
+ - Stable-Baselines3: 1.7.0
4
+ - PyTorch: 1.13.1+cu117
5
  - GPU Enabled: True
6
+ - Numpy: 1.24.1
7
  - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b810bd6cf2694875d55623c805bc48e2944b7fb112d42e6ae0106a9e037f3059
3
- size 254923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200e7c62cf2aab54b828219db6ff554400e43d5433897b837086c0d9c36029b1
3
+ size 194479
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 217.0, "std_reward": 79.69316156358713, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-09T21:51:16.165287"}
 
1
+ {"mean_reward": 677.0, "std_reward": 93.65361712181756, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-11T07:29:50.531767"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8137134b7ce91ab9cf06b8a42ee89694c8bb3832ffa472aab3b731cc814491cf
3
- size 41628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd8ae398533637f3813f2c77ea15a7c3ee22155672b2a37d35cc99d5c3d3a20
3
+ size 303669