paper-with-me

홈 › Papers

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 an approximation of the underlying model of the RL environment and then use it in combination with planning algorithms. Upside-Down Reinforcement Learning (UDRL) is a novel learning paradigm that aims to learn how to predict actions from states and desired commands. This task is formulated as a Supervised Learning problem and has successfully been tackled by Neural Networks (NNs). In this paper, we investigate whether function approximation algorithms other than NNs can also be used within a UDRL framework. Our experiments, performed over several popular optimal control benchmarks, show that tree-based methods like Random Forests and Extremely Randomized Trees can perform just as well as NNs with the significant benefit of resulting in policies that are inherently more interpretable than NNs, therefore paving the way for more transparent, safe, and robust RL.

📄 PDF Abstract BibTeX arXiv:2411.11457

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

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…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Training Agents using Upside-Down Reinforcement Learning

2019-12-05 · Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz, Wojciech Jaśkowski 외

We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use reward prediction or search for an optimal po…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

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 Can Diverge in Stochastic Environments With Episodic Resets

2022-05-13 · Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley, Jürgen Schmidhuber 외

Upside-Down Reinforcement Learning (UDRL) is an approach for solving RL problems that does not require value functions and uses only supervised learning, where the targets for given inputs in a dataset do not change over…

reinforcement-learningReinforcement Learning (RL)

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