Parametrized Quantum Policies for Reinforcement Learning.
Sofiène JerbiCasper GyurikSimon MarshallHans J. BriegelVedran DunjkoPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- markov decision processes
- state space
- control policies
- control policy
- reward function
- markov decision problems
- partially observable markov decision processes
- fitted q iteration
- reinforcement learning agents
- cooperative multi agent systems
- function approximation
- policy gradient methods
- total reward
- hierarchical reinforcement learning
- dynamic programming
- machine learning
- macro actions
- decision problems
- reinforcement learning algorithms
- continuous state
- model free
- quantum inspired
- quantum computing
- average cost
- policy iteration
- finite state
- temporal difference learning
- supervised learning
- optimal control
- average reward
- logic circuits
- learning process
- infinite horizon
- learning algorithm
- robotic control
- approximate policy iteration
- multiagent reinforcement learning
- temporal difference
- multi agent
- transfer learning
- partially observable
- learning problems