Hugging Face's logo

chaouch
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
chaouch commited on
Commit
4693387
·
1 Parent(s): 1b3b657

all

Browse files
Files changed (9) hide show
  1. args.yml +1 -1
  2. config.yml +8 -8
  3. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  5. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +4 -4
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3637567795
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 160830502
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -8,22 +8,22 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
- - 496
16
  - - learning_rate
17
- - 0.0003
18
  - - learning_starts
19
- - 0
20
  - - n_timesteps
21
- - 1015808
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - -1
28
  - - train_freq
29
- - 1024
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
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
  - 4
14
  - - gradient_steps
15
+ - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
+ - 1000000.0
20
  - - n_timesteps
21
+ - 1000000.0
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 sha256:2c19c464a3dd29abbb49d5ec7f5b8e310dcfee7be071eae21a1203c423461d06
3
- size 27220220
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1f6282d1c0d2906cdf6d57f71f280c5279354fbdf817a35680adfdf86d0520
3
+ size 13715027
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 sha256:12b2653ea4e0ac71202f15119c9ab677a8a6f97bbc6886f70c974914676888e7
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
+ size 1120
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f96393c9c06d496a4cd1a1d7931e216159b200c48f5969b1a2ce9d9b6518ca9
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c38d865f86856ed2fe47e0e02126da9d99c8a33e6b26026f1e2c51fe4c5bc42
3
  size 13505370
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: 2.3.0a2
4
- - PyTorch: 2.1.0+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: Linux-6.5.0-21-generic-x86_64-with-glibc2.35 # 21~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 9 13:32:52 UTC 2
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0a2
4
+ - PyTorch: 2.2.1+cu121
5
  - GPU Enabled: True
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": 347.5, "std_reward": 178.86097953438588, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-22T12:44:46.141421"}
 
1
+ {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T10:00:58.942785"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90ea8b0766e3cc6d92032c6280f644fd2b9469203986dbd8524741eb7823bfc2
3
- size 19485
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48cec9db3c8bd7e57f87828dc6511a609f586f72d88a9ec540d263cc477fb27a
3
+ size 48435