paper-with-me

Papers

Dynamical Priors as a Training Objective in Reinforcement Learning

2026-04-23 · Sukesh Subaharan arxiv

Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as abrupt confidence shifts, oscillations, or degenerate inactivity. We introduce Dynamical Prior Reinforcement Learning (DP-RL), a training framework that augments policy gradient learning with an auxiliary loss derived from external state dynamics that implement evidence accumulation and hysteresis. Without modifying the reward, environment, or policy architecture, this prior shapes the temporal evolution of action probabilities during learning. Across three minimal environments, we show that dynamical priors systematically alter decision trajectories in task-dependent ways, promoting temporally structured behavior that cannot be explained by generic smoothing. These results demonstrate that training objectives alone can control the temporal geometry of decision-making in RL agents.

📄 PDF Abstract BibTeX arXiv:2604.21464

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion

2025-07-01 · Ziang Zheng, Guojian Zhan, Shiqi Liu, Yao Lyu 외 arxiv

Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underact…

Reinforcement Learning

SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning

2022-05-26 · Marco Bagatella, Sammy Christen, Otmar Hilliges

Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on comp…

continuous-controlContinuous ControlDeep Reinforcement LearningEfficient Exploration+3

Solving Bayesian inverse problems with diffusion priors and off-policy RL

2025-03-12 · Luca Scimeca, Siddarth Venkatraman, Moksh Jain, Minsu Kim 외

This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (RL) objective that can asymptotically solve Bayesian inverse problems optimally. …

Reinforcement Learning (RL)

A Hierarchical Bayesian Linear Regression Model with Local Features for Stochastic Dynamics Approximation

2018-07-11 · Behnoosh Parsa, Keshav Rajasekaran, Franziska Meier, Ashis G. Banerjee

One of the challenges in model-based control of stochastic dynamical systems is that the state transition dynamics are involved, and it is not easy or efficient to make good-quality predictions of the states. Moreover, t…

Model-based Reinforcement LearningregressionReinforcement Learning

Tackling the Zero-Shot Reinforcement Learning Loss Directly

2025-02-15 · Yann Ollivier

Zero-shot reinforcement learning (RL) methods aim at instantly producing a behavior for an RL task in a given environment, from a description of the reward function. These methods are usually tested by evaluating their a…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)