Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making.
Nishant DesaiAndrew CritchStuart J. RussellPublished in: NeurIPS (2018)
Keyphrases
- sequential decision making
- pareto optimal
- reinforcement learning
- expected utility
- multi objective
- interactive dynamic influence diagrams
- multi objective optimization
- multiple objectives
- function approximation
- nash equilibrium
- multi issue negotiation
- machine learning
- temporal difference
- nsga ii
- state space
- pareto optimal set
- reinforcement learning algorithms
- optimal solution
- evolutionary algorithm
- multi agent
- decision problems
- markov decision processes
- model free
- optimization algorithm
- dynamic programming
- objective function
- optimal policy
- influence diagrams
- supervised learning
- upper bound
- cooperative
- learning algorithm