Reward Function

Reward functions, crucial for guiding reinforcement learning agents towards desired behaviors, are the focus of intense research. Current efforts center on automatically learning reward functions from diverse sources like human preferences, demonstrations (including imperfect ones), and natural language descriptions, often employing techniques like inverse reinforcement learning, large language models, and Bayesian optimization within various architectures including transformers and generative models. This research is vital for improving the efficiency and robustness of reinforcement learning, enabling its application to complex real-world problems where manually designing reward functions is impractical or impossible. The ultimate goal is to create more adaptable and human-aligned AI systems.

Papers

April 12, 2022

Learning Performance Graphs from Demonstrations via Task-Based Evaluations
Aniruddh G. Puranic, Jyotirmoy V. Deshmukh, Stefanos Nikolaidis
Global Evaluation Reward Function Noisy Demonstration Performance Analysis Provided Demonstration

March 25, 2022

Preprocessing Reward Functions for Interpretability
Erik Jenner, Adam Gleave
Inherent Interpretability Reward Function Interpretability Tool

March 22, 2022

A Primer on Maximum Causal Entropy Inverse Reinforcement Learning
Adam Gleave, Sam Toyer
Reward Function Inverse Reinforcement Learning Causal Entropy

March 20, 2022

Reinforcement learning reward function in unmanned aerial vehicle control tasks
Mikhail S. Tovarnov, Nikita V. Bykov
Deep Reinforcement Learning Reward Function Positive Reinforcement Drone Control Deep Reinforcement Learning Algorithm

March 18, 2022

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning
Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee
Reinforcement Learning Data Augmentation Reward Function Reward Learning Preference Based Reinforcement Learning Semi Supervised Reward

March 14, 2022

March 13, 2022

DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning
Jinxin Liu, Hongyin Zhang, Donglin Wang
Offline Reinforcement Learning Reward Function Offline Deep Reinforcement Learning

March 9, 2022

Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading
Federico Cornalba, Constantin Disselkamp, Davide Scassola, Christopher Helf
Deep Reinforcement Learning Financial Application System Performance Reward Function Single Objective

March 8, 2022

R\'enyi State Entropy for Exploration Acceleration in Reinforcement Learning
Mingqi Yuan, Man-on Pun, Dong Wang
Reinforcement Learning Reward Function Intrinsic Reward Rapid Exploration Entropy Maximization R\'enyi Entropy

February 25, 2022

Context-Hierarchy Inverse Reinforcement Learning
Wei Gao, David Hsu, Wee Sun Lee
Reward Function Inverse Reinforcement Learning Complex Reward Function

February 24, 2022

Learning Transferable Reward for Query Object Localization with Policy Adaptation
Tingfeng Li, Shaobo Han, Martin Renqiang Min, Dimitris N. Metaxas
Reinforcement Learning Reward Function Ordinal Pattern Policy Adaptation

February 21, 2022

Inferring Lexicographically-Ordered Rewards from Preferences
Alihan Hüyük, William R. Zame, Mihaela van der Schaar
Reinforcement Learning Reward Function Preference Feedback Reward Report Explanatory Inference Multiple Objective

February 16, 2022

Open-Ended Reinforcement Learning with Neural Reward Functions
Robert Meier, Asier Mujika
High Dimensional Unsupervised Learning Reward Function Open Ended

February 13, 2022

Individual-Level Inverse Reinforcement Learning for Mean Field Games
Yang Chen, Libo Zhang, Jiamou Liu, Shuyue Hu
Reward Function Inverse Reinforcement Learning Collective Behavior Mean Field Game Large Scale Multi Agent Mean Field Reinforcement Learning

February 1, 2022

A General, Evolution-Inspired Reward Function for Social Robotics
Thomas Kingsford
Reward Function Social Robot General Text Social Robotics Social Reward

January 28, 2022

January 25, 2022

Dynamics-Aware Comparison of Learned Reward Functions
Blake Wulfe, Ashwin Balakrishna, Logan Ellis, Jean Mercat, Rowan McAllister, Adrien Gaidon
Reward Function Reward Learning

January 17, 2022

Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learning
Keuntaek Lee, David Isele, Evangelos A. Theodorou, Sangjae Bae
Autonomous Driving Reward Function Inverse Reinforcement Learning Cost Map Deep Inverse Reinforcement Learning