Transfer in Reinforcement Learning via Regret Bounds for Learning Agents.
Adrienne TuynmanRonald OrtnerPublished in: CoRR (2022)
Keyphrases
- learning agents
- reinforcement learning
- multi armed bandit
- regret bounds
- transfer learning
- learning agent
- function approximation
- multi agent
- lower bound
- complex environments
- multiagent systems
- autonomous agents
- reinforcement learning algorithms
- markov decision processes
- machine learning
- online learning
- model free
- state space
- single agent
- special case
- bayesian networks
- learning algorithm
- maximum likelihood
- learning tasks
- linear regression
- reward function
- dynamic programming
- learning capabilities
- multi agent systems