TractOracle: towards an anatomically-informed reward function for RL-based tractography.
Antoine ThébergeMaxime DescoteauxPierre-Marc JodoinPublished in: CoRR (2024)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- state space
- optimal policy
- partially observable
- white matter
- markov decision process
- multiple agents
- inverse reinforcement learning
- hierarchical reinforcement learning
- learning agent
- model free
- function approximation
- transition probabilities
- dynamic programming
- multi agent
- learning algorithm
- agent learns
- generative model
- reward signal
- initially unknown
- particle filter
- temporal difference
- average reward
- decision problems