When is Realizability Sufficient for Off-Policy Reinforcement Learning?
Andrea ZanettePublished in: ICML (2023)
Keyphrases
- reinforcement learning
- function approximation
- control problems
- markov decision processes
- machine learning
- reinforcement learning algorithms
- robotic control
- learning algorithm
- state space
- supervised learning
- model free
- temporal difference
- multi agent
- learning capabilities
- optimal policy
- optimal control
- real time
- control system
- data sets