BY571 / D4PG-ray

Distributed PyTorch implementation of D4PG with ray. Using a SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

d4pg ray distributed-computing iqn ddpg continuous-action-space reinforcement-learning-algorithms reinforcement-learning state-of-the-art

D4PG-ray

TODO:

Clear / clean code
Do testruns for LunarLander // Pendulum
Make comparisons of all features
Make Readme
Add PER

About

Distributed PyTorch implementation of D4PG with ray. Using a SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

d4pg ray distributed-computing iqn ddpg continuous-action-space reinforcement-learning-algorithms reinforcement-learning state-of-the-art

Languages

Language:Python 100.0%