DeepAI
Log In Sign Up

Provable Multi-Objective Reinforcement Learning with Generative Models

11/19/2020
by   Dongruo Zhou, et al.
8

Multi-objective reinforcement learning (MORL) is an extension of ordinary, single-objective reinforcement learning (RL) that is applicable to many real world tasks where multiple objectives exist without known relative costs. We study the problem of single policy MORL, which learns an optimal policy given the preference of objectives. Existing methods require strong assumptions such as exact knowledge of the multi-objective Markov decision process, and are analyzed in the limit of infinite data and time. We propose a new algorithm called model-based envelop value iteration (EVI), which generalizes the enveloped multi-objective Q-learning algorithm in Yang, 2019. Our method can learn a near-optimal value function with polynomial sample complexity and linear convergence speed. To the best of our knowledge, this is the first finite-sample analysis of MORL algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/09/2016

Multi-Objective Deep Reinforcement Learning

We propose Deep Optimistic Linear Support Learning (DOL) to solve high-d...
11/16/2022

Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning

Multi-objective reinforcement learning (MORL) is a relatively new field ...
07/03/2021

Multi-Objective Congestion Control

Decades of research on Internet congestion control (CC) has produced a p...
06/05/2021

Dynamic Resource Configuration for Low-Power IoT Networks: A Multi-Objective Reinforcement Learning Method

Considering grant-free transmissions in low-power IoT networks with unkn...
11/08/2018

Meta-Learning for Multi-objective Reinforcement Learning

Multi-objective reinforcement learning (MORL) is the generalization of s...
09/26/2019

Relationship Explainable Multi-objective Reinforcement Learning with Semantic Explainability Generation

Solving multi-objective optimization problems is important in various ap...
10/02/2019

Relationship Explainable Multi-objective Optimization Via Vector Value Function Based Reinforcement Learning

Solving multi-objective optimization problems is important in various ap...