Resilient Constrained Reinforcement Learning.
Dongsheng DingZhengyan HuanAlejandro RibeiroPublished in: AISTATS (2024)
Keyphrases
- reinforcement learning
- function approximation
- state space
- temporal difference
- markov decision processes
- case study
- optimal control
- transfer learning
- optimal policy
- learning process
- data sets
- least squares
- learning algorithm
- neural network
- real time
- dynamic programming
- decision trees
- genetic algorithm
- machine learning
- model free
- reinforcement learning algorithms
- control problems
- function approximators
- stochastic approximation
- direct policy search