Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs.
Aria HasanzadeZonuzyArchana BuraDileep M. KalathilSrinivas ShakkottaiPublished in: AAAI (2021)
Keyphrases
- reinforcement learning
- learning problems
- sample complexity
- learning algorithm
- supervised learning
- learning process
- sample complexity bounds
- markov decision processes
- active learning
- theoretical analysis
- learning tasks
- upper bound
- lower bound
- decision lists
- data sets
- transfer learning
- concept learning
- partially observable
- linear threshold
- machine learning
- special case
- multi agent
- decision trees
- temporal difference
- policy search