A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning.
Long YangMinhao ShiQian ZhengWenjia MengGang PanPublished in: IJCAI (2018)
Keyphrases
- temporal difference learning
- multi step
- eligibility traces
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- state space
- model free
- reinforcement learning methods
- policy evaluation
- markov decision processes
- function approximators
- k nearest neighbor
- knn
- policy iteration
- transfer learning
- machine learning
- reward function
- learning algorithm
- nearest neighbor
- markov decision process
- semi supervised
- fixed point
- supervised learning