More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling.
Haque IshfaqYixin TanYu YangQingfeng LanJianfeng LuA. Rupam MahmoodDoina PrecupPan XuPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- active exploration
- model free
- computationally expensive
- markov decision processes
- sample size
- balancing exploration and exploitation
- uniform sampling
- reinforcement learning algorithms
- learning problems
- cost effective
- neural network
- optimal policy
- computationally efficient
- supervised learning
- state space
- data structure
- case study
- machine learning
- data mining