Reinforcement Learning based Decoding Using Internal Reward for Time Delayed Task in Brain Machine Interfaces.
Xiang ShenXiang ZhangYifan HuangShuhang ChenYiwen WangPublished in: EMBC (2020)
Keyphrases
- reinforcement learning
- function approximation
- eligibility traces
- reinforcement learning algorithms
- state space
- multi agent
- human brain
- model free
- markov decision processes
- learning algorithm
- batch processing
- dynamic programming
- optimal policy
- total reward
- sensory inputs
- learning agent
- decoding process
- internal and external
- flowshop
- partially observable environments
- user interface
- reward function
- action space
- temporal difference
- transfer learning
- decoding algorithm
- reinforcement learning methods
- markov decision process
- brain images
- reward shaping
- agent receives