R×R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training.
Gagan KhandateTristan Luca SaidiSiqi ShangEric T. ChangYang LiuSeth DennisJohnson AdamsMatei T. CiocarliePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- exploration strategy
- function approximation
- active exploration
- supervised learning
- action selection
- probability distribution
- state space
- training and test data
- exploration exploitation
- machine learning
- markov decision processes
- learning problems
- multi agent
- transfer learning
- model free
- optimal policy
- training algorithm
- training phase
- training examples
- reinforcement learning algorithms
- training set
- learning algorithm
- monte carlo
- motion planning
- temporal difference
- heavy tailed
- online learning