d4pg

Here are 8 public repositories matching this topic...

denisyarats / pytorch_sac

PyTorch implementation of Soft Actor-Critic (SAC)

reinforcement-learning deep-learning deep-reinforcement-learning pytorch gym sac continuous-control actor-critic mujoco dm-control soft-actor-critic d4pg

Updated Dec 5, 2021
Jupyter Notebook

schatty / oprl

Star

A Modular Library for Off-Policy Reinforcement Learning with a focus on SafeRL and distributed computing

pytorch d4pg ddpg-pytorch

Updated Jul 25, 2024
Python

BY571 / D4PG

Star

PyTorch implementation of D4PG with the 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.

reinforcement-learning ddpg deep-deterministic-policy-gradient iqn prioritized-experience-replay actor-critic-algorithm pytorch-implementation distributional-rl d4pg munchausen-reinforcement-learning nstep-bootstrapping d2rl

Updated Apr 7, 2021
Python

derektan95 / Deep-Reinforcement-Learning-Algorithms

Star

A collection of algorithms for Deep Reinforcement Learning (DRL). Algorithms covered include Value-Based, Policy-Based and Actor-Critic Methods.

crawler robotics unity deep-reinforcement-learning soccer pytorch dqn tennis udacity-nanodegree ddpg multi-agent-systems robotic-arm ppo unity-ml-agents d4pg

Updated Feb 18, 2023
Jupyter Notebook

tyranitar / continuous-control

Star

A2C and D4PG implementations for the continuous control challenge. Part of the coursework for Udacity's Deep RL Nanodegree.

gae deep-reinforcement-learning continuous-control a2c d4pg

Updated Apr 15, 2022
Python

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.

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