Hugging Face's logo

Victarry
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Victarry commited on
Commit
da76383
•
1 Parent(s): 57688b3

Initial commit

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. args.yml +83 -0
  3. config.yml +29 -0
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +3 -0
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +3 -0
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +3 -0
  9. dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth +3 -0
  10. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +7 -0
  11. env_kwargs.yml +1 -0
  12. replay.mp4 +3 -0
  13. results.json +1 -0
  14. train_eval_metrics.zip +3 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - dqn
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - SpaceInvadersNoFrameskip-v4
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 5
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs/
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 1
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 2921498542
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - ''
64
+ - - track
65
+ - false
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - null
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
82
+ - - yaml_file
83
+ - null
config.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - 1000000.0
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f055416d9141acc8990186ce10f7bfb4bf2b63f5c1d6a26e158734a5bf1efdc5
3
+ size 27225029
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.7.0
dqn-SpaceInvadersNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde3961830db37bca2e8a9ebe176e7c3f86e1b384af8d18d6db89b7ee56108ee
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de3d00e963b069b0a4ea3846af5692a2eba2c7ab5f3ba1f5b87bfd40a8ab268
3
+ size 13504937
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.13.0-41-generic-x86_64-with-glibc2.17 # 46~20.04.1-Ubuntu SMP Wed Apr 20 13:16:21 UTC 2022
2
+ - Python: 3.8.13
3
+ - Stable-Baselines3: 1.7.0
4
+ - PyTorch: 1.12.1
5
+ - GPU Enabled: True
6
+ - Numpy: 1.23.1
7
+ - Gym: 0.21.0
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0523cb7af66481112dff5f06d9fa0d44df2f711c8e50d4b70d60816b6cecdcfa
3
+ size 206537
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 568.5, "std_reward": 78.868561543875, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-11T08:15:15.248690"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf15653be7b8235dda5ecc7c1595d225454a8b84ef3eeda46ce2ae13c7c96b54
3
+ size 37091