/DDPG

Tensorflow implementation of Deep Deterministic Policy Gradients

Primary LanguagePython

DDPG

Tensorflow implementation of Deep deterministic policy gradient

Paper Continuous control with deep reinforcement learning

Examples:

Pendumlum

python ddpg_main.py

Results: pendulum-v0

MountainCarContinuous-v0

python ddpg_main.py -env_name='MountainCarContinuous-v0'

Results: MountainCarContinuous-v0

LunarLanderContinuous-v2

python ddpg_main.py -env_name='LunarLanderContinuous-v2'

Results: LunarLanderContinuous-v2