State-space Model Based Inverse Reinforcement Learning for Reward Function Estimation in Brain-machine Interfaces.
Jieyuan TanXiang ZhangShenghui WuYiwen WangPublished in: EMBC (2023)
Keyphrases
- monte carlo
- reward function
- state space
- inverse reinforcement learning
- markov chain
- particle filter
- markov decision processes
- reinforcement learning algorithms
- reinforcement learning
- transition probabilities
- temporal difference
- optimal policy
- partially observable
- markov decision process
- state variables
- state transition
- dynamic programming
- search space
- multiple agents
- dynamic systems
- dynamical systems
- model free
- generative model
- hidden markov models