Three Dogmas of Reinforcement Learning.
David AbelMark K. HoAnna HarutyunyanPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- robotic control
- control problems
- temporal difference
- state space
- function approximation
- multi agent
- reinforcement learning algorithms
- model free
- markov decision processes
- transfer learning
- multi agent reinforcement learning
- machine learning
- optimal policy
- learning process
- sufficient conditions
- supervised learning
- active learning
- learning capabilities
- decision making
- real robot
- function approximators
- artificial intelligence
- learning algorithm