NorbertRop commited on
Commit
72c6527
1 Parent(s): 4de825a

Initial commit

Browse files
.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
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - SpaceInvadersNoFrameskip-v4
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: QRDQN
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: SpaceInvadersNoFrameskip-v4
16
+ type: SpaceInvadersNoFrameskip-v4
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 2380.00 +/- 1021.83
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **QRDQN** Agent playing **SpaceInvadersNoFrameskip-v4**
25
+ This is a trained model of a **QRDQN** agent playing **SpaceInvadersNoFrameskip-v4**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
+
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
+
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ ```
40
+ # Download model and save it into the logs/ folder
41
+ python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga NorbertRop -f logs/
42
+ python enjoy.py --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
43
+ ```
44
+
45
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
46
+ ```
47
+ python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga NorbertRop -f logs/
48
+ rl_zoo3 enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
49
+ ```
50
+
51
+ ## Training (with the RL Zoo)
52
+ ```
53
+ python train.py --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
54
+ # Upload the model and generate video (when possible)
55
+ python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga NorbertRop
56
+ ```
57
+
58
+ ## Hyperparameters
59
+ ```python
60
+ OrderedDict([('env_wrapper',
61
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
62
+ ('exploration_fraction', 0.025),
63
+ ('frame_stack', 4),
64
+ ('n_timesteps', 10000000.0),
65
+ ('optimize_memory_usage', True),
66
+ ('policy', 'CnnPolicy'),
67
+ ('replay_buffer_kwargs', {'handle_timeout_termination': False}),
68
+ ('normalize', False)])
69
+ ```
args.yml ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - qrdqn
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
+ - true
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 2278474354
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
+ - - yaml_file
81
+ - null
config.yml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - env_wrapper
3
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
4
+ - - exploration_fraction
5
+ - 0.025
6
+ - - frame_stack
7
+ - 4
8
+ - - n_timesteps
9
+ - 10000000.0
10
+ - - optimize_memory_usage
11
+ - true
12
+ - - policy
13
+ - CnnPolicy
14
+ - - replay_buffer_kwargs
15
+ - handle_timeout_termination: false
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
qrdqn-SpaceInvadersNoFrameskip-v4.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421cdc4e664450b2b26eea3d1b1b0e5f15760d702cf642ce2bd56a97479488a3
3
+ size 37025441
qrdqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.7.0a10
qrdqn-SpaceInvadersNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4a5d70fb13d574d70b127c45a28244470b9ad0171853ab2aefa5e445a6f2b8
3
+ size 18405963
qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19d90be5f922d73855840e1610918ddd842e81c12b53b19b925ff98cc02e2ea
3
+ size 18405545
qrdqn-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
qrdqn-SpaceInvadersNoFrameskip-v4/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ OS: Linux-5.15.0-56-generic-x86_64-with-glibc2.35 #62-Ubuntu SMP Tue Nov 22 19:54:14 UTC 2022
2
+ Python: 3.10.6
3
+ Stable-Baselines3: 1.7.0a10
4
+ PyTorch: 1.13.1+cu117
5
+ GPU Enabled: True
6
+ Numpy: 1.24.0
7
+ Gym: 0.21.0
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d946231620f424d684eddbf28d9cc3412f28957e9a6d696e1e82fa8cb568d90a
3
+ size 188153
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 2380.0, "std_reward": 1021.8316886845896, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-25T21:30:20.561722"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e5ba2c3e23066d1536cc1ab5355f95559657db9ac4b78fc69c449d215b98103
3
+ size 249606