meln1k commited on
Commit
6ffde56
1 Parent(s): 2e23e45

Initial commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.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: DQN
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 817.50 +/- 327.32
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: SpaceInvadersNoFrameskip-v4
20
+ type: SpaceInvadersNoFrameskip-v4
21
+ ---
22
+
23
+ # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
24
+ This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
25
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
26
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
27
+
28
+ The RL Zoo is a training framework for Stable Baselines3
29
+ reinforcement learning agents,
30
+ with hyperparameter optimization and pre-trained agents included.
31
+
32
+ ## Usage (with SB3 RL Zoo)
33
+
34
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
35
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
36
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
37
+
38
+ ```
39
+ # Download model and save it into the logs/ folder
40
+ python -m utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga meln1k -f logs/
41
+ python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga meln1k
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('batch_size', 32),
54
+ ('buffer_size', 100000),
55
+ ('env_wrapper',
56
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
57
+ ('exploration_final_eps', 0.01),
58
+ ('exploration_fraction', 0.1),
59
+ ('frame_stack', 4),
60
+ ('gradient_steps', 1),
61
+ ('learning_rate', 0.0001),
62
+ ('learning_starts', 100000),
63
+ ('n_timesteps', 1000000.0),
64
+ ('optimize_memory_usage', True),
65
+ ('policy', 'CnnPolicy'),
66
+ ('target_update_interval', 1000),
67
+ ('train_freq', 4),
68
+ ('normalize', False)])
69
+ ```
args.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - dqn
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - SpaceInvadersNoFrameskip-v4
8
+ - - env_kwargs
9
+ - null
10
+ - - eval_episodes
11
+ - 5
12
+ - - eval_freq
13
+ - 25000
14
+ - - gym_packages
15
+ - []
16
+ - - hyperparams
17
+ - null
18
+ - - log_folder
19
+ - logs/
20
+ - - log_interval
21
+ - -1
22
+ - - max_total_trials
23
+ - null
24
+ - - n_eval_envs
25
+ - 1
26
+ - - n_evaluations
27
+ - null
28
+ - - n_jobs
29
+ - 1
30
+ - - n_startup_trials
31
+ - 10
32
+ - - n_timesteps
33
+ - -1
34
+ - - n_trials
35
+ - 500
36
+ - - no_optim_plots
37
+ - false
38
+ - - num_threads
39
+ - -1
40
+ - - optimization_log_path
41
+ - null
42
+ - - optimize_hyperparameters
43
+ - false
44
+ - - pruner
45
+ - median
46
+ - - sampler
47
+ - tpe
48
+ - - save_freq
49
+ - -1
50
+ - - save_replay_buffer
51
+ - false
52
+ - - seed
53
+ - 3950883432
54
+ - - storage
55
+ - null
56
+ - - study_name
57
+ - null
58
+ - - tensorboard_log
59
+ - runs/SpaceInvadersNoFrameskip-v4__dqn__3950883432__1654879661
60
+ - - track
61
+ - true
62
+ - - trained_agent
63
+ - ''
64
+ - - truncate_last_trajectory
65
+ - true
66
+ - - uuid
67
+ - false
68
+ - - vec_env
69
+ - dummy
70
+ - - verbose
71
+ - 1
72
+ - - wandb_entity
73
+ - null
74
+ - - wandb_project_name
75
+ - unit3-dqn-space-invaders
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
+ - true
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 sha256:5f9211cc80549870d24a3c983e16cde72fa29cc9936ed4dff22a3a1267245442
3
+ size 27222421
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a7
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 sha256:21549da738935ef83e83040208e4f06bf06dac1ce61be9d342ea0910c620d52c
3
+ size 13503145
dqn-SpaceInvadersNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4d4451b2dd88c674be293605652eb6f2e9030b6e636541d29ffa40e15ec219
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-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021
2
+ Python: 3.9.12
3
+ Stable-Baselines3: 1.5.1a7
4
+ PyTorch: 1.11.0+cu102
5
+ GPU Enabled: True
6
+ Numpy: 1.22.3
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:ffae42df2843a0da664ad5261e7e61a576fd2f746411d38d56327873656a0f0b
3
+ size 200625
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 817.5, "std_reward": 327.3243803935173, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-10T19:30:39.802920"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:247a44b18b2b0a9bd426c8c2d7e2a3e675100b96e0a03f0448baefeadc153e2b
3
+ size 36535