2014 · 31 citations · 11 references
ComputingComputer ScienceAlgorithmsMachine LearningOptimizationExploration-exploitation TradeoffMulti-agent SystemsMulti-objective OptimizationMultiobjective OptimizationPolicy LearningReinforcement LearningCoverageMulti-agent Reinforcement LearningMultiobjective Reinforcement LearningPareto Front ComputationReward Trade-off Analysis
To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the scalarization function and the learned policy makes the discovery of system wide trade-offs time consuming. Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi-objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.
11
Empirical evaluation methods for multiobjective reinforcement learning algorithms
Peter Vamplew, Richard Dazeley, Adam Berry et al. · Machine Learning · 2010 · 274 citations · Full text
Linear Fitted-Q Iteration with Multiple Reward Functions.
Daniel J. Lizotte, Michael Bowling, Susan A. Murphy · PubMed · 2012 · 71 citations