Adaptive and multiple time-scale eligibility traces for online deep reinforcement learning.
Taisuke KobayashiPublished in: Robotics Auton. Syst. (2022)
Keyphrases
- eligibility traces
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- reinforcement learning methods
- multi agent
- dynamic programming
- state space
- machine learning
- learning algorithm
- optimal policy
- adaptive control
- learning process
- linear programming
- temporal difference
- policy evaluation