Fairness in Reinforcement Learning with Bisimulation Metrics

2024-12-22 · Sahand Rezaei-Shoshtari, Hanna Yurchyk, Scott Fujimoto, Doina Precup, David Meger

Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments. By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. In this paper, we establish the connection between bisimulation metrics and group fairness in reinforcement learning. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics, ensuring that learners treat groups fairly while reflecting the original problem. We demonstrate the effectiveness of our method in addressing disparities in sequential decision making problems through empirical evaluation on a standard fairness benchmark consisting of lending and college admission scenarios.

📄 PDF Abstract BibTeX arXiv:2412.17123

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making Fairness reinforcement-learning Reinforcement LearningSequential Decision Making

Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation

2022-01-28 · Martin Bertran, Walter Talbott, Nitish Srivastava, Joshua Susskind

Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning. Recently, there has been renewed interest in bisimulation metrics as a tool to…

Data Augmentation Reinforcement Learning (RL)Semantic Similarity Semantic Textual Similarity

Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions

2023-02-12 · Qiyuan Liu, Qi Zhou, Rui Yang, Jie Wang

Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to …

Clustering Reinforcement Learning (RL)Representation Learning

Approximate Policy Iteration with Bisimulation Metrics

2022-02-06 · Mete Kemertas, Allan Jepson

Bisimulation metrics define a distance measure between states of a Markov decision process (MDP) based on a comparison of reward sequences. Due to this property they provide theoretical guarantees in value function appro…

Continuous Control Representation Learning

Invariant Representations for Reinforcement Learning without Reconstruction

2021-01-01 · ICLR 2021 1 · Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal 외

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations …

Causal Inference MuJoCo reinforcement-learning Reinforcement Learning+2

Learning Invariant Representations for Reinforcement Learning without Reconstruction

2020-06-18 · Amy Zhang, Rowan McAllister, Roberto Calandra, Yarin Gal 외