A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation.
Runzhe YangXingyuan SunKarthik NarasimhanPublished in: CoRR (2019)
Keyphrases
- multi objective
- optimization algorithm
- learning algorithm
- reinforcement learning
- computational complexity
- objective function
- cost function
- convergence rate
- preprocessing
- expectation maximization
- computational cost
- dynamic programming
- simulated annealing
- optimal solution
- genetic algorithm
- worst case
- model free
- k means
- probabilistic model
- evolutionary algorithm
- search space
- search algorithm
- monte carlo
- markov decision processes
- benchmark problems
- solution quality
- action space