Model-Based and Model-Free Replay Mechanisms for Reinforcement Learning in Neurorobotics.
Elisa MassiJeanne BarthélemyJuliane MaillyRémi DromnelleJulien CanitrotEsther PoniatowskiBenoît GirardMehdi KhamassiPublished in: Frontiers Neurorobotics (2022)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- policy iteration
- temporal difference
- rl algorithms
- policy evaluation
- state space
- reinforcement learning methods
- optimal policy
- machine learning
- average reward
- learning problems
- pattern recognition
- function approximators
- markov decision processes
- dynamic programming
- neural network
- impedance control