Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms
원문 초록
Learning in high dimensional continuous tasks is challenging, mainly when the experience replay memory is very limited. We introduce a simple yet effective experience sharing mechanism for deterministic policies in continuous action domains for the future off-policy deep reinforcement learning applications in which the allocated memory for the experience replay buffer is limited. To overcome the extrapolation error induced by learning from other agents' experiences, we facilitate our algorithm with a novel off-policy correction technique without any action probability estimates. We test the effectiveness of our method in challenging OpenAI Gym continuous control tasks and conclude that it can achieve a safe experience sharing across multiple agents and exhibits a robust performance when the replay memory is strictly limited.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
rQdia: Regularizing Q-Value Distributions With Image Augmentation
Safe Planning and Policy Optimization via World Model Learning
CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum
토론
이 논문과 연결된 포럼 글이 아직 없습니다.