Hugging Face's logo

HadrienCr
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
HadrienCr commited on
Commit
4a5e53a
·
1 Parent(s): 7c002e8

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  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. 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: 343.00 +/- 201.26
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,14 +63,14 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
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', 0.0005),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 500000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 416.50 +/- 162.77
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 120000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.025),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 500000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1188493635
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4232570936
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,11 +2,11 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.01
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0005
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 120000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.025
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
 
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:be668ee41c3f4e086edf1d1f7b9c8d8f9074dcfb030a07e442475fb917598666
3
- size 27220785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:719f5ed36980c4067d29d2c8e43eca87b0d1aae14f07993d28b7e6fea747fb1a
3
+ size 27220787
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:dfdece7e6411cf0e4654620ca3d0059338b9f82c1d6d71a6227757ba96531136
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a064e989c5b379803f87934cfd21caa462a04a4a89a461c246b93b2928d213
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97f0f691df0c1d4871e2c5702a9aaec2bf7ed52fefdb9d24a725a428fa1e1a3e
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1071e54a130d0490a8bec6bc52c9ca7c06d8e9abede297b70722762c59e38f8c
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7c9cfeb0a56e28c9a54c5633373ac3b57542debe3072f248542c1cdbe1f3ae9
3
- size 295597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2746363886e7bd973b3ef8571fbc1aef0d49bb0fdb123e7eb7673b11e2725b65
3
+ size 259984
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 343.0, "std_reward": 201.26102454275642, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-16T10:36:50.752322"}
 
1
+ {"mean_reward": 416.5, "std_reward": 162.77361579813848, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-16T15:07:54.293741"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d9f4a25d7d348daf935ea756af6d3ed4ea641b77cdb690a80ed5ae0e96d2572
3
- size 20684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815c3a8648a1446095645d5fbe8d8ad5f89fd63875f500dfe3c0181b430bf0fc
3
+ size 21751