Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration.
Anji LiuYitao LiangGuy Van den BroeckPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- model based reinforcement learning
- exploration exploitation
- function approximation
- autonomous learning
- state space
- exploration exploitation tradeoff
- temporal difference
- reinforcement learning algorithms
- markov decision processes
- machine learning
- optimal policy
- robotic control
- learning algorithm
- deep learning
- temporal difference learning
- database
- learning problems
- decision making
- relational reinforcement learning
- website
- policy search
- multi agent reinforcement learning
- multi agent
- robot control
- dynamic programming
- model free
- optimal control