Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping

Lauren H. Cooke, Harvey Klyne, Edwin Zhang, Cassidy Laidlaw, Milind Tambe +1 more
12/15/2023
cs.LGcs.AIstat.ML

No confident code implementation found for this paper.

Abstract

Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce the computational burden of each RL sub-problem. This work serves as a proof-of-concept and we hope will inspire future developments towards computationally efficient IRL.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Advances in Preference-based Reinforcement Learning: A Review

89% match2024

Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach

87% match1 repo2222024

Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise

87% match2025

Model Selection for Inverse Reinforcement Learning via Structural Risk Minimization

87% match2023

Subgoal-based Hierarchical Reinforcement Learning for Multi-Agent Collaboration

87% match1 repo102024

Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques

86% match2024

Cite this paper

@article{cooke2023toward,
  title  = {Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping},
  author = {Lauren H. Cooke and Harvey Klyne and Edwin Zhang and Cassidy Laidlaw and Milind Tambe and Finale Doshi-Velez},
  year   = {2023},
  eprint = {2312.09983},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.09983v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.09983.svg)](https://codeofpaper.com/paper/2312.09983)

Discussion