Minimax-Bayes Reinforcement Learning.
Thomas Kleine BueningChristos DimitrakakisHannes ErikssonDivya GroverEmilio JorgePublished in: AISTATS (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- temporal difference
- learning algorithm
- decision trees
- evaluation function
- support vector
- markov decision processes
- optimal policy
- optimal control
- model free
- temporal difference learning
- game tree
- machine learning
- markov decision process
- transfer learning
- supervised learning
- support vector machine
- multi agent reinforcement learning
- policy search
- multi agent
- robotic control
- conditionally independent
- autonomous learning
- interval estimation
- learning problems
- bayes classifier
- robot control
- dynamic programming
- hidden markov models
- objective function
- training data
- genetic algorithm