Disturbing Reinforcement Learning Agents with Corrupted Rewards.
Rubén MajadasJavier GarcíaFernando FernándezPublished in: CoRR (2021)
Keyphrases
- reinforcement learning agents
- reinforcement learning
- state abstraction
- dynamic environments
- markov decision processes
- multi agent
- state space
- function approximation
- reinforcement learning algorithms
- learning algorithm
- transfer learning
- multi agent environments
- machine learning
- model free
- optimal policy
- temporal difference