Multi-Objective Deep Reinforcement Learning (2016-10-09T00:00:00.000000Z)

TL;DR

This work proposes Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori.

Abstract

We propose Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the first time that deep reinforcement learning has succeeded in learning multi-objective policies. In addition, we provide a testbed with two experiments to be used as a benchmark for deep multi-objective reinforcement learning.

Authors

Shimon Whiteson

13 papers

Yannis Assael

6 papers

D. Roijers

4 papers

TL;DR

Abstract

Authors

References36 items

Visual Attention

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

Mastering the game of Go with deep neural networks and tree search

Increasing the Action Gap: New Operators for Reinforcement Learning

Variational Multi−Objective Coordination

Dueling Network Architectures for Deep Reinforcement Learning

Prioritized Experience Replay

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

Deep Reinforcement Learning with Double Q-Learning

Action-Conditional Video Prediction using Deep Networks in Atari Games

Point-Based Planning for Multi-Objective POMDPs

Massively Parallel Methods for Deep Reinforcement Learning

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

End-to-End Training of Deep Visuomotor Policies

Human-level control through deep reinforcement learning

Move Evaluation in Go Using Deep Convolutional Neural Networks

Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning

Model-based multi-objective reinforcement learning

A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

The scalarized multi-objective multi-armed bandit problem: An empirical study of its exploration vs. exploitation tradeoff

A Survey of Multi-Objective Sequential Decision-Making

Empirical evaluation methods for multiobjective reinforcement learning algorithms

Solving Multi-objective Reinforcement Learning Problems by EDA-RL - Acquisition of Various Strategies

Learning all optimal policies with multiple criteria

Managing Power Consumption and Performance of Computing Systems Using Reinforcement Learning

Dynamic preferences in multi-criteria reinforcement learning

Evolutionary Algorithms for Solving Multi-Objective Problems

Multi-objective decision-theoretic planning

Computing Convex Coverage Sets for Faster Multi-objective Coordination

Pareto Local Search for MOMDP Planning

Variational Multi-Objective Coordination

Multi-objective reinforcement learning using sets of pareto dominating policies

The gesture recognition toolkit

Algorithms for partially observable markov decision processes

Reinforcement Learning for Robots Using Neural Networks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names