Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning.
Jung-Su HaYoung-Jin ParkHyeok-Joo ChaeSoon-Seo ParkHan-Lim ChoiPublished in: CoRR (2020)
Keyphrases
- action selection
- reinforcement learning
- control policy
- optimal policy
- control policies
- reinforcement learning problems
- partially observable
- planning problems
- hierarchical reinforcement learning
- control strategies
- markov decision problems
- hierarchical representation
- optimal control
- function approximation
- long run
- adaptive control
- policy search
- control rules
- control problems
- robot control
- markov decision process
- control system
- partially observable markov decision processes
- partially observable environments
- hierarchical decomposition
- partially observable domains
- policy iteration
- reinforcement learning algorithms
- markov decision processes
- action space
- blocks world
- partial observability
- policy gradient
- transition model
- temporal difference
- control strategy
- image representation
- macro actions
- state space
- multi agent