paper-with-me

Papers

Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective

2024-06-03 · Sindre Benjamin Remman, Bjørn Andreas Kristiansen, Anastasios M. Lekkas

In this work, we use optimal control to change the behavior of a deep reinforcement learning policy by optimizing directly in the policy's latent space. We hypothesize that distinct behavioral patterns, termed behavioral modes, can be identified within certain regions of a deep reinforcement learning policy's latent space, meaning that specific actions or strategies are preferred within these regions. We identify these behavioral modes using latent space dimension-reduction with \ac*{pacmap}. Using the actions generated by the optimal control procedure, we move the system from one behavioral mode to another. We subsequently utilize these actions as a filter for interpreting the neural network policy. The results show that this approach can impose desired behavioral modes in the policy, demonstrated by showing how a failed episode can be made successful and vice versa using the lunar lander reinforcement learning environment.

📄 PDF Abstract BibTeX arXiv:2406.01178

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningDimensionality Reductionreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching

2024-04-27 · Robert Denkert, Huyên Pham, Xavier Warin

We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling a…

Policy Gradient Methods

To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning

2024-07-01 · Tao Ma, Xuzhi Yang, Zoltan Szabo

Reinforcement learning (RL) -- finding the optimal behaviour (also referred to as policy) maximizing the collected long-term cumulative reward -- is among the most influential approaches in machine learning with a large …

Offline RLReinforcement Learning (RL)

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation

2023-11-26 · Heyang Zhao, Jiafan He, Quanquan Gu

The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-Learning with Upper Confidence Bound (MQ…

Q-LearningReinforcement Learning (RL)

Understanding Mode Switching in Human-AI Collaboration: Behavioral Insights and Predictive Modeling

2025-09-25 · Avinash Ajit Nargund, Arthur Caetano, Kevin Yang, Rose Yiwei Liu 외 arxiv

Human-AI collaboration is typically offered in one of two of user control levels: guidance, where the AI provides suggestions and the human makes the final decision, and delegation, where the AI acts autonomously within …

Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective

2026-03-09 · Liyuan Mao, Le Yu, Jing Zhou, Chujie Zheng 외 arxiv

In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exposed through token-conditional generatio…

Reinforcement LearningQuestion Answering