Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret.
Han ZhongJiachen HuYecheng XueTongyang LiLiwei WangPublished in: CoRR (2023)
Keyphrases
- worst case
- reinforcement learning
- lower bound
- average case
- upper bound
- greedy algorithm
- np hard
- function approximation
- error bounds
- approximation algorithms
- quantum computation
- state space
- quantum computing
- quantum mechanics
- multi agent
- running times
- theoretical guarantees
- temporal difference
- computational complexity
- reinforcement learning algorithms
- information retrieval
- machine learning
- logic circuits
- online algorithms
- action selection
- optimal policy
- special case
- action space
- learning algorithm
- e learning
- temporal difference learning
- markov decision processes
- transfer learning
- quantum inspired