reward-shaping

salesforce/MultiHopKG

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

lcswillems/torch-ac

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

yining043/NeuOpt

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.

csmile-1006/ARP

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

kochlisGit/TraderNet-CRv2

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

niksaz/dota2-expert-demo

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

holarissun/RewardShifting

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

mike-gimelfarb/bayesian-reward-shaping

Bayesian Reward Shaping Framework for Deep Reinforcement Learning

awilliea/Risk-based_RL_for_Optimal_Trading_Execution

jbakams/slimebot-volleyball

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

tongzhoumu/DrS

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

zhang-zengjie/Reward4Driving

Benchmarks for risk-aware reward shaping of autonomous driving

Digitalized-Energy-Systems/opfgym

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.

Eugene1533/snake-ai-pytorch-complexification

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

takato86/shaper

Reward shaping library

dylwil3/reward-shaping

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

PoldervaartS/RLRLGym

Reinforcement Learning Exploration of PPO and training methods in Rocket League

brianwade1/Gym_QLearning_and_RewardShaping

This repo demonstrates basic Q-learning for the Mountain Car Gym environment. It also shows how reward shaping can result in faster training of the agent.

CAmayoral/hello-world

BAT Basic Attention Token, Brave, Uphold, DAPP, Cryptocurrenies.

IngyN/macsrl

Project for a semi-centralized logic-based MARL reward shaping method that is scalable in the number of agents and evaluates it in multiple scenarios

johnHostetter/PolicyPrep

Prepares policies from data to model; focuses on hierarchical tasks and applies reward shaping to handle delayed reward signals.

lara-martin/StoryPlot-RewardShaping

Code from the IJCAI 2019 paper "Controllable Neural Story Plot Generation via Reward Shaping"

RedLeader962/Une-intuition-sur-RUDDER

Ressources pour la présentation orale: "Une intuition sur RUDDER (Return Decomposition for Delayed Rewards)"

ChiragRadhakrishna43-7/Pacman_MultiAgents

Pacman games with multi agents. Evaluating the performance of Pacman and the ghosts.

tanu10/RLPeri

[AAAI 2024] RLPeri: Accelerating Visual Perimetry Test with Reinforcement Learning and Convolutional Feature Extraction