Efficient Reinforcement Learning using Gaussian Processes

This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model...

Mô tả đầy đủ

Đã lưu trong:

Chi tiết về thư mục
Tác giả chính:	Deisenroth, Marc Peter
Định dạng:	Online
Ngôn ngữ:	Tiếng Anh
Được phát hành:	KIT Scientific Publishing 2021
Những chủ đề:	QA75.5-76.95 autonomous learning Gaussian processes control machine learning Bayesian inference bic Book Industry Communication::U Computing & information technology::UY Computer science
Truy cập trực tuyến:	35389
Các nhãn:	Thêm thẻ Không có thẻ, Là người đầu tiên thẻ bản ghi này!

Miêu tả
Tóm tắt:	This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems.

Efficient Reinforcement Learning using Gaussian Processes

Những quyển sách tương tự