arXiv:1905.09275
공식 코드 · Papers with Code
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
원문 초록
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.
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
Deep Reinforcement Learning with Gradient Eligibility Traces
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.