Bootstrapping Expectiles in Reinforcement Learning.
Pierre ClavierEmmanuel RachelsonErwan Le PennecMatthieu GeistPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- direct policy search
- machine learning
- learning algorithm
- reinforcement learning algorithms
- information extraction
- robotic control
- supervised learning
- optimal policy
- model free
- learning problems
- relation extraction
- weakly supervised
- continuous state
- transition model
- policy search
- markov decision processes
- dynamic programming
- multi agent
- neural network
- learning classifier systems
- temporal difference
- real time
- state space
- markov decision process
- learning agent
- control system
- social networks