We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
abstract. Analytical investigations of agency are mostly concerned with a description ex post acto. However, continuous action (being doing something) needs to be considered as wel...
Although several researchers have integrated methods for reinforcement learning (RL) with case-based reasoning (CBR) to model continuous action spaces, existing integrations typic...
Abstract— We present a simple randomized POMDP algorithm for planning with continuous actions in partially observable environments. Our algorithm operates on a set of reachable b...