Model-Free Non-Stationarity Detection and Adaptation in Reinforcement Learning.
Giuseppe CanonacoMarcello RestelliManuel RoveriPublished in: ECAI (2020)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- policy iteration
- policy evaluation
- rl algorithms
- state space
- learning algorithm
- learning process
- pattern recognition
- multi agent
- average reward
- reinforcement learning methods
- dynamic programming
- supervised learning
- markov decision processes
- partially observable