The Differentiable Cross-Entropy Method
원문 초록
We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function's parameters. In the machine learning setting this brings CEM inside of the end-to-end learning pipeline where this has otherwise been impossible. We show applications in a synthetic energy-based structured prediction task and in non-convex continuous control. In the control setting we show how to embed optimal action sequences into a lower-dimensional space. DCEM enables us to fine-tune CEM-based controllers with policy optimization.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Improving Value Estimation Critically Enhances Vanilla Policy Gradient
RLBenchNet: The Right Network for the Right Reinforcement Learning Task
Guided Policy Optimization under Partial Observability
Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.