Non-Markovian Reinforcement Learning using Fractional Dynamics.
Gaurav GuptaChenzhong YinJyotirmoy V. DeshmukhPaul BogdanPublished in: CDC (2021)
Keyphrases
- reinforcement learning
- reinforcement learning agents
- state space
- function approximation
- dynamic model
- reward function
- optimal policy
- partially observable domains
- model free
- markov decision processes
- temporal difference
- learning algorithm
- machine learning
- robotic control
- least squares
- dynamic programming
- action selection
- transfer learning
- reinforcement learning algorithms
- markov decision process
- temporal difference learning
- data sets