Task-agnostic Exploration in Reinforcement Learning.
Xuezhou ZhangYuzhe MaAdish SinglaPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- exploration exploitation
- model based reinforcement learning
- markov decision processes
- function approximation
- reinforcement learning algorithms
- temporal difference
- autonomous learning
- control problems
- model free
- state space
- transfer learning
- optimal policy
- learning process
- supervised learning
- dynamic programming
- multi agent
- decision making
- learning algorithm
- data sets
- exploration exploitation tradeoff
- balancing exploration and exploitation
- policy search
- reinforcement learning methods
- temporal difference learning
- action space
- learning problems
- active learning
- machine learning
- neural network