Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
README.md		README.md
agent.py		agent.py
config.py		config.py
main.py		main.py
model.py		model.py
replay_memory.py		replay_memory.py
summary.png		summary.png
test.gif		test.gif

Repository files navigation

LunarLander

Reinforcement Learning with Paddle PARL

Training Result

Converges to about 210 after about 100 episodes

Evaluation

About

Reinforcement Learning with Paddle PARL

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%