Zobrazeno 1 - 3
of 3
pro vyhledávání: '"62L20, 68T05"'
Autor:
Lauand, Caio Kalil, Meyn, Sean
Many machine learning and optimization algorithms are built upon the framework of stochastic approximation (SA), for which the selection of step-size (or learning rate) is essential for success. For the sake of clarity, this paper focuses on the spec
Externí odkaz:
http://arxiv.org/abs/2405.17834
Autor:
Jia, Yanwei
This paper studies continuous-time risk-sensitive reinforcement learning (RL) under the entropy-regularized, exploratory diffusion process formulation with the exponential-form objective. The risk-sensitive objective arises either as the agent's risk
Externí odkaz:
http://arxiv.org/abs/2404.12598
Autor:
Lauand, Caio Kalil, Meyn, Sean
Theory and application of stochastic approximation (SA) has grown within the control systems community since the earliest days of adaptive control. This paper takes a new look at the topic, motivated by recent results establishing remarkable performa
Externí odkaz:
http://arxiv.org/abs/2309.02944