paper-with-me

홈 › Papers

Actor-Critic with variable time discretization via sustained actions

2023-08-08 · Jakub Łyskawa, Paweł Wawrzyński

Reinforcement learning (RL) methods work in discrete time. In order to apply RL to inherently continuous problems like robotic control, a specific time discretization needs to be defined. This is a choice between sparse time control, which may be easier to train, and finer time control, which may allow for better ultimate performance. In this work, we propose SusACER, an off-policy RL algorithm that combines the advantages of different time discretization settings. Initially, it operates with sparse time discretization and gradually switches to a fine one. We analyze the effects of the changing time discretization in robotic control environments: Ant, HalfCheetah, Hopper, and Walker2D. In all cases our proposed algorithm outperforms state of the art.

📄 PDF Abstract BibTeX arXiv:2308.04299

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule

2026-01-26 · Yilie Huang, Wenpin Tang, Xunyu Zhou arxiv

We consider time discretization for score-based diffusion models to generate samples from a learned reverse-time dynamic on a finite grid. Uniform and hand-crafted grids can be suboptimal given a budget on the number of …

Reinforcement Learning

Making Deep Q-learning methods robust to time discretization

2019-01-28 · Corentin Tallec, Léonard Blier, Yann Ollivier

Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sen…

Deep Reinforcement LearningQ-LearningReinforcement LearningSensitivity

Analysing Rescaling, Discretization, and Linearization in RNNs for Neural System Modelling

2023-12-26 · Mariano Caruso, Cecilia Jarne

Recurrent Neural Networks (RNNs) are widely used for modelling neural activity, yet the mathematical interplay of core procedures is used to analyze them (temporal rescaling, discretization, and linearization) remain unc…

Decision Making

Mars Entry Trajectory Planning with Range Discretization and Successive Convexification

2022-01-24 · Xu Liu, Shuang Li, Ming Xin

This paper develops a sequential convex programming approach for Mars entry trajectory planning by range discretization. To improve the accuracy of numerical integration, the range of entry trajectory is selected as the …

Numerical IntegrationTrajectory Planning

Basin-Preserving Discretizations of Modern Hopfield Retrieval Dynamics: Energy Cells, Dissipation, and the Attention Limit

2026-08-21 · Francisco R. Villatoro arxiv

The retrieval dynamics of a modern Hopfield network is the gradient flow of a log-sum-exp energy, while the attention update is its exact difference-of-convex minimization step. We study which time discretizations preser…