paper-with-me

홈 › Papers

Learning Relative Return Policies With Upside-Down Reinforcement Learning

2022-02-23 · Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber, Rupesh Kumar Srivastava

Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems. Recent work in this area has largely focused on learning command-conditioned policies. We investigate the potential of one such method -- upside-down reinforcement learning -- to work with commands that specify a desired relationship between some scalar value and the observed return. We show that upside-down reinforcement learning can learn to carry out such commands online in a tabular bandit setting and in CartPole with non-linear function approximation. By doing so, we demonstrate the power of this family of methods and open the way for their practical use under more complicated command structures.

📄 PDF Abstract BibTeX arXiv:2202.12742

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Upside Down Reinforcement Learning with Policy Generators

2025-01-27 · Jacopo Di Ventura, Dylan R. Ashley, Vincent Herrmann, Francesco Faccio 외

Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning …

reinforcement-learningReinforcement Learning

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

2022-02-24 · Kai Arulkumaran, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh K. Srivastava

Upside down reinforcement learning (UDRL) flips the conventional use of the return in the objective function in RL upside down, by taking returns as input and predicting actions. UDRL is based purely on supervised learni…

AllImitation LearningOffline RLreinforcement-learning+1

Upside-Down Reinforcement Learning for More Interpretable Optimal Control

2024-11-18 · Juan Cardenas-Cartagena, Massimiliano Falzari, Marco Zullich, Matthia Sabatelli

Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to expected rewards or search for policies that can maximize a certain performance function. Model-Based algorithms instead, aim to learn a…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

2021-10-27 · ICML Workshop URL 2021 7 · Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier, Alessandro Lazaric 외

Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of diverse skills that provide a thorough cove…

On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers

2025-02-08 · Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley 외

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed com…

reinforcement-learningReinforcement Learning