Hugging Face's logo

krisha-n
/
dqn-SpaceInvadersNoFrameskip-v4-2

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
krisha-n commited on
Commit
82618aa
•
1 Parent(s): ae00990

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +7 -7
  2. args.yml +1 -1
  3. config.yml +6 -6
  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 +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +6 -6
  10. results.json +1 -1
  11. 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: 109.50 +/- 88.47
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,17 +62,17 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 64),
66
- ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.2),
71
- ('frame_stack', 3),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
75
- ('n_timesteps', 50000),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 492.00 +/- 80.88
20
  name: mean_reward
21
  verified: false
22
  ---
 
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', 100000),
75
+ ('n_timesteps', 1000000),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 912211317
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3616035638
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,24 +1,24 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.2
12
  - - frame_stack
13
- - 3
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 50000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
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
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.1
12
  - - frame_stack
13
+ - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
+ - 1000000
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 sha256:79f44709aa6f6ec1a023b1755fc075575d2e543c6ccb680b23adeb17cc507af8
3
- size 27138675
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55f44a67d6c73f90a4796ac565b3f8a95716f2f37b2751269040da48269b49d
3
+ size 27219319
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:de5416081b9a3b9de2e687df0689298cd3220f26d200842a72982bcd6594f6d1
3
- size 13489788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd049e44b8d0ba28dc733ee430fa681c7730ebaff606735ae2c8b234c9d7022
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f36ae31afb3c8dc82c750928b793c9df0835141821694c89c3530251845ae943
3
- size 13488986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883fbf8ac59ec00224b1fc5629d6838cb6a4a9b3f8f1dfcef19f36a1bd240741
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
  size 864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4dde0c1ad63b7740276006a06cc491b21b407ea6c889928c223ec77ddad79f
3
  size 864
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
- - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0
4
- - PyTorch: 2.2.1+cu121
5
- - GPU Enabled: True
6
- - Numpy: 1.25.2
7
- - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
 
1
+ - OS: Windows-10-10.0.22000-SP0 10.0.22000
2
+ - Python: 3.10.14
3
  - Stable-Baselines3: 2.3.0
4
+ - PyTorch: 2.2.2+cpu
5
+ - GPU Enabled: False
6
+ - Numpy: 1.26.4
7
+ - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 109.5, "std_reward": 88.47174690261292, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T10:28:04.200871"}
 
1
+ {"mean_reward": 492.0, "std_reward": 80.876448982383, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-14T08:06:27.857187"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffe5428102761d346aebb8a84b09af692de0af835134348602428db642af685d
3
- size 3060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0881d659e4a21cae7bed6f075010ecb410479507d9564386ba639b5a84d3d8
3
+ size 36454