Actor-critic versus direct policy search: a comparison based on sample complexity
원문 초록
Sample efficiency is a critical property when optimizing policy parameters for the controller of a robot. In this paper, we evaluate two state-of-the-art policy optimization algorithms. One is a recent deep reinforcement learning method based on an actor-critic algorithm, Deep Deterministic Policy Gradient (DDPG), that has been shown to perform well on various control benchmarks. The other one is a direct policy search method, Covariance Matrix Adaptation Evolution Strategy (CMA-ES), a black-box optimization method that is widely used for robot learning. The algorithms are evaluated on a continuous version of the mountain car benchmark problem, so as to compare their sample complexity. From a preliminary analysis, we expect DDPG to be more sample efficient than CMA-ES, which is confirmed by our experimental results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Deep Reinforcement Learning with Gradient Eligibility Traces
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning
Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management
토론
이 논문과 연결된 포럼 글이 아직 없습니다.