LazyAct: Lazy actor with dynamic state skip based on constrained MDP.

ABSTRACT: Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. Specifically, each decision made by an agent requires a complete neural network computation, leading to a linear increase in computational cost with the number of interactions and agents. Inspired by human decision-making patterns, which involve reasoning only on critical states in continuous decision-making tasks without considering all states, we introduce the LazyAct algorithm. This algorithm significantly reduces the number of inferences while preserving the quality of the policy. Firstly, we incorporate a state skipping branch into the actor network to bypass states with mini

SUBMITTER: Zhang H 

PROVIDER: S-EPMC11801576 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature