A Boosting Approach to Reinforcement Learning.
Nataly BrukhimElad HazanKaran SinghPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- function approximation
- reinforcement learning algorithms
- optimal policy
- machine learning
- state space
- cost sensitive
- markov decision processes
- feature selection
- learning problems
- markov decision process
- boosting algorithms
- model free
- learning classifier systems
- base classifiers
- ensemble methods
- dynamic programming
- multi agent
- multi agent reinforcement learning
- policy search
- robotic control
- gradient boosting
- data sets
- weak learners
- adaboost algorithm
- temporal difference
- neural network