Mildly Constrained Evaluation Policy for Offline Reinforcement Learning.
Linjie XuZhengyao JiangJinyu WangLei SongJiang BianPublished in: Trans. Mach. Learn. Res. (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- evaluation method
- real time
- markov decision processes
- markov decision process
- reinforcement learning algorithms
- reward function
- evaluation methods
- function approximation
- machine learning
- partially observable environments
- dynamic programming
- learning process
- learning algorithm
- policy iteration
- robotic control
- markov decision problems
- function approximators
- optimal control
- partially observable
- action selection
- model free
- state space
- genetic algorithm
- neural network