RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code

Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO

This repo implements our paper, "Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt", which has been accepted at NeurIPS 2023.

Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)

TraderNet-CRv2 - Combining Deep Reinforcement Learning with Technical Analysis and Trend Monitoring on Cryptocurrency Markets

Dota 2 bot that is trained by Deep RL with expert demonstrations

Code for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL

Bayesian Reward Shaping Framework for Deep Reinforcement Learning

Implementation of Humanoid Standing Up, from the paper "Learning Humanoid Standing-up Control across Diverse Postures" out of Shanghai, in Pytorch

Code for "DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks"

3D gym environments to train RL agents to play the Slime Volleyball game in 3 dimensions using Webots as simulator.

Benchmarks for risk-aware reward shaping of autonomous driving

A gymnasium-compatible framework to create reinforcement learning (RL) environment for solving the optimal power flow (OPF) problem. Contains five OPF benchmark environments for comparable research.

Set of experiments of using weights of a previously trained network as prior knowledge for a more complicated one and reward providing.

Reward shaping library

A lightweight package for running small experiments with reward shaping in reinforcement learning.

Reinforcement Learning Exploration of PPO and training methods in Rocket League

This repo empirically investigates that Weight Agnostic Neural Networks (WANN) are a promising alternative to traditional RL models in sparse settings.