Variational quantum policies for reinforcement learning.
Sofiène JerbiCasper GyurikSimon MarshallHans J. BriegelVedran DunjkoPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- markov decision processes
- function approximation
- reward function
- policy gradient methods
- reinforcement learning algorithms
- partially observable markov decision processes
- state space
- fitted q iteration
- total reward
- control policy
- learning algorithm
- quantum computation
- reinforcement learning agents
- markov decision problems
- macro actions
- quantum computing
- image segmentation
- machine learning
- quantum mechanics
- temporal difference
- optical flow
- infinite horizon
- learning process
- hierarchical reinforcement learning
- robotic control
- model free
- methods in computer vision
- long run
- management policies
- continuous state
- variational methods
- function approximators
- action space
- multi agent
- sufficient conditions
- access control
- information retrieval
- quantum inspired
- image processing
- dynamic programming
- optical flow computation
- image sequences
- policy iteration