Skip to content

Deep Deterministic Policy Gradients RL algo

Notifications You must be signed in to change notification settings

tellingmachine/DDPG-Mountain-Car

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 

Repository files navigation

DDPG-Mountain-Car

DDPG algo

My simple notebook implementation of the DDPG actor-critic algorithm from https://arxiv.org/pdf/1509.02971.pdf It uses and solves OpenAI Gym's Continuous Mountain Car environment.

Note: this code is quite hacky and not written in vectorized form for higher dimensional problems. Batch Norm is not used.

For more details on the Continuous Mountain Car problem see my blog at https://medium.com/@asteinbach/actor-critic-using-deep-rl-continuous-mountain-car-in-tensorflow-4c1fb2110f7c for a description of code. This blog uses a simpler actor-critic algo rather than DDPG

For the theory of this simpler actor-critic algo see my blog at https://medium.com/@asteinbach/rl-introduction-simple-actor-critic-for-continuous-actions-4e22afb712

About

Deep Deterministic Policy Gradients RL algo

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published