Hugging Face's logo

hammadsaleem
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
hammadsaleem commited on
Commit
3b8384c
·
1 Parent(s): ca0615f

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: 6.50 +/- 5.94
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ 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),
@@ -71,11 +71,11 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 100000),
75
- ('n_timesteps', 10000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
- ('target_update_interval', 700),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 183.00 +/- 101.00
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 20000),
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', 1000),
75
+ ('n_timesteps', 20000.0),
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
- - 2377852112
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2124080804
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
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
- - 100000
20
  - - n_timesteps
21
- - 10000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - 700
28
  - - train_freq
29
  - 4
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 20000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 1000
20
  - - n_timesteps
21
+ - 20000.0
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 sha256:3b53738373843e8ce207637f1b3b92ce711355a92578ff49daf90e2b6e176fba
3
- size 13711495
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be9b8f99ed448c2ba17e043ab5bb7cdf0a175b8bff9961ea45e89a4d989b643
3
+ size 27216974
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:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef9276d17a925a86ea52a26f59e80e506e0899d65c5b46ba0b15b2b427ac527
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c700bb55d658df2b47b575dec8369b3f2319226c64d78de02c3986e5e992e13
3
  size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3200dcd7d69244416ff4af5483c9216e08325fc4d1ecc434459e0f0b71b8209e
3
  size 13505178
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c09044cb80a802ca22de420b9b50337387cce3028de7092fa83adcdb5aac5e21
3
- size 267542
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d29af8f470558491f05726ac2603f7a87a7da4e9b38f52dc3d660af860b745e
3
+ size 283144
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 6.5, "std_reward": 5.937171043518958, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-30T21:14:45.487508"}
 
1
+ {"mean_reward": 183.0, "std_reward": 101.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-30T21:31:43.328083"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0ab29a79ed1929651f5f40df3d7af85245c44fd72862d65a5ffa243636e5381
3
- size 586
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab15f8d1fed57ca3d1cce2a2d1bca6f1dc73a1a83054cc552738773f0a0f31a6
3
+ size 1013