Detecting Rewards Deterioration in Episodic Reinforcement Learning.
Ido GreenbergShie MannorPublished in: ICML (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- state space
- model free
- multi agent
- dynamic programming
- reward shaping
- transfer learning
- optimal policy
- supervised learning
- reinforcement learning algorithms
- data sets
- infinite horizon
- temporal difference
- policy iteration
- temporal difference learning
- reinforcement learning methods
- multi agent reinforcement learning
- learning process