Popular GitHub Repositories for D4pg

PyTorch implementation of Soft Actor-Critic (SAC)

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.

Multi-agent reinforcement learning where an agent learns to play tennis against itself. Part of the coursework for Udacity's Deep RL Nanodegree.