Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach.
Yingjie FeiZhuoran YangZhaoran WangPublished in: ICML (2021)
Keyphrases
- function approximation
- risk sensitive
- model free
- reinforcement learning
- optimal control
- markov decision processes
- reinforcement learning algorithms
- markov decision problems
- temporal difference
- control policies
- function approximators
- temporal difference learning
- state space
- utility function
- policy iteration
- optimal policy
- partially observable
- expected utility
- machine learning
- radial basis function
- learning tasks
- decision theoretic
- transfer learning
- action space
- dynamic programming
- reinforcement learning methods
- control strategies
- action selection
- monte carlo
- control policy
- average reward
- support vector
- decision making
- learning algorithm
- data mining