Prepares policies from data to model; focuses on hierarchical tasks and applies reward shaping to handle delayed reward signals.
-
Updated
Jun 26, 2024 - Python
Prepares policies from data to model; focuses on hierarchical tasks and applies reward shaping to handle delayed reward signals.
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.
Code from the IJCAI 2019 paper "Controllable Neural Story Plot Generation via Reward Shaping"
[AAAI 2024] RLPeri: Accelerating Visual Perimetry Test with Reinforcement Learning and Convolutional Feature Extraction
Pacman games with multi agents. Evaluating the performance of Pacman and the ghosts.
Reinforcement Learning Exploration of PPO and training methods in Rocket League
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
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.
Bayesian Reward Shaping Framework for Deep Reinforcement Learning
Code for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL
Dota 2 bot that is trained by Deep RL with expert demonstrations
Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code
Add a description, image, and links to the reward-shaping topic page so that developers can more easily learn about it.
To associate your repository with the reward-shaping topic, visit your repo's landing page and select "manage topics."