A practical guide to multi-objective reinforcement learning and planning.
Conor F. HayesRoxana RadulescuEugenio BargiacchiJohan KällströmMatthew MacfarlaneMathieu ReymondTimothy VerstraetenLuisa M. ZintgrafRichard DazeleyFredrik HeintzEnda HowleyAthirai A. IrissappanePatrick MannionAnn NowéGabriel de Oliveira RamosMarcello RestelliPeter VamplewDiederik M. RoijersPublished in: Auton. Agents Multi Agent Syst. (2022)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- multiobjective optimization
- action selection
- genetic algorithm
- objective function
- partially observable
- state space
- heuristic search
- multiple objectives
- reinforcement learning algorithms
- macro actions
- function approximation
- multi objective optimization problems
- markov decision processes
- reinforcement learning problems
- particle swarm optimization
- conflicting objectives
- nsga ii
- pareto optimal
- model free
- multi agent
- deterministic domains
- partially observable markov decision processes
- bi objective
- neural network
- partial observability
- complex domains
- genetic programming
- decision support
- multi objective evolutionary
- stochastic domains
- blocks world
- process planning
- planning process
- multi objective evolutionary algorithms
- single agent
- learning classifier systems
- utility function
- domain independent
- optimal policy
- learning process
- learning algorithm