Rooba
/
lightning
mirror of https://github.com/Lightning-AI/lightning.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Organize docstring (#4906) 

* Organize docstring

* Update pl_examples/domain_templates/reinforce_learn_Qnet.py

Co-authored-by: Jirka Borovec <Borda@users.noreply.github.com>

Co-authored-by: Jirka Borovec <Borda@users.noreply.github.com>
Co-authored-by: chaton <thomas@grid.ai>
This commit is contained in:
Lucien 2020-12-04 21:45:13 +08:00 committed by GitHub
parent 88792982b5
commit d3626b7f50
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
pl_examples/domain_templates/reinforce_learn_Qnet.py
View File

@ -1,19 +1,22 @@
"""
Deep Reinforcement Learning: Deep Q-network (DQN)
This example is based on https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-
Second-Edition/blob/master/Chapter06/02_dqn_pong.py
The template illustrates using Lightning for Reinforcement Learning. The example builds a basic DQN using the
classic CartPole environment.
To run the template, just run:
python reinforce_learn_Qnet.py
`python reinforce_learn_Qnet.py`
After ~1500 steps, you will see the total_reward hitting the max score of 200. Open up TensorBoard to
see the metrics:
After ~1500 steps, you will see the total_reward hitting the max score of 200.
Open up TensorBoard to see the metrics:
tensorboard --logdir default
`tensorboard --logdir default`
References
----------
[1] https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-
Second-Edition/blob/master/Chapter06/02_dqn_pong.py
"""
import argparse