paper-with-me

Papers

Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle

2019-07-11 · Guojun Wu, Yanhua Li, Zhenming Liu, Jie Bao, Yu Zheng, Jieping Ye, Jun Luo

Many real-world human behaviors can be characterized as a sequential decision making processes, such as urban travelers choices of transport modes and routes (Wu et al. 2017). Differing from choices controlled by machines, which in general follows perfect rationality to adopt the policy with the highest reward, studies have revealed that human agents make sub-optimal decisions under bounded rationality (Tao, Rohde, and Corcoran 2014). Such behaviors can be modeled using maximum causal entropy (MCE) principle (Ziebart 2010). In this paper, we define and investigate a general reward trans-formation problem (namely, reward advancement): Recovering the range of additional reward functions that transform the agent's policy from original policy to a predefined target policy under MCE principle. We show that given an MDP and a target policy, there are infinite many additional reward functions that can achieve the desired policy transformation. Moreover, we propose an algorithm to further extract the additional rewards with minimum "cost" to implement the policy transformation.

📄 PDF Abstract BibTeX arXiv:1907.05390

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingSequential Decision Making

Similar Papers 제목 키워드 기반

Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures

2024-12-09 · Adrien Bolland, Gaspard Lambrechts, Damien Ernst

We introduce a new maximum entropy reinforcement learning framework based on the distribution of states and actions visited by a policy. More precisely, an intrinsic reward function is added to the reward function of the…

reinforcement-learningReinforcement Learning

BiCQL-ML: A Bi-Level Conservative Q-Learning Framework for Maximum Likelihood Inverse Reinforcement Learning

2025-11-27 · Junsung Park arxiv

Offline inverse reinforcement learning (IRL) aims to recover a reward function that explains expert behavior using only fixed demonstration data, without any additional online interaction. We propose BiCQL-ML, a policy-f…

Reinforcement LearningOffline RL

Reward-Punishment Reinforcement Learning with Maximum Entropy

2024-05-20 · Jiexin Wang, Eiji Uchibe

We introduce the ``soft Deep MaxPain'' (softDMP) algorithm, which integrates the optimization of long-term policy entropy into reward-punishment reinforcement learning objectives. Our motivation is to facilitate a smooth…

reinforcement-learningReinforcement Learning

A maximum-entropy approach to off-policy evaluation in average-reward MDPs

2020-06-17 · NeurIPS 2020 12 · Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine 외

This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs). For MDPs that are ergodic and linear (i.e. where rewards and dynamics are li…

Off-policy evaluation

Information Theoretic Guarantees For Policy Alignment In Large Language Models

2024-06-09 · Youssef Mroueh

Policy alignment of large language models refers to constrained policy optimization, where the policy is optimized to maximize a reward while staying close to a reference policy with respect to an $f$-divergence such as …