English
Related papers

Related papers: Completion vs Optimality: Policy Gradient in Long-…

200 papers

The solution of a constrained linear-quadratic regulator problem is determined by the set of its optimal active sets. We propose an algorithm that constructs this set of active sets for a desired horizon N from that for horizon N-1. While…

Optimization and Control · Mathematics 2020-09-21 Ruth Mitze , Martin Mönnigmann

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…

Machine Learning · Computer Science 2024-05-31 Weiye Zhao , Feihan Li , Yifan Sun , Rui Chen , Tianhao Wei , Changliu Liu

We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the policy update and the representation. textcolor{blue}{First},…

Machine Learning · Computer Science 2025-04-04 Jincheng Mei , Bo Dai , Alekh Agarwal , Mohammad Ghavamzadeh , Csaba Szepesvari , Dale Schuurmans

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by decomposing tasks, most existing methods rely on separate high- and low-level networks and…

Machine Learning · Computer Science 2026-02-04 Jinwoo Choi , Sang-Hyun Lee , Seung-Woo Seo

Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only…

Machine Learning · Computer Science 2024-06-27 Yu Luo , Fuchun Sun , Tianying Ji , Xianyuan Zhan

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

Machine Learning · Computer Science 2025-05-26 Ben Rahman

Model Predictive Control has emerged as a popular tool for robots to generate complex motions. However, the real-time requirement has limited the use of hard constraints and large preview horizons, which are necessary to ensure safety and…

A typical bottleneck of model predictive control algorithms is the computational burden in order to compute the receding horizon feedback law which is predominantly determined by the length of the prediction horizon. Based on a relaxed…

Optimization and Control · Mathematics 2014-01-16 Jürgen Pannek , Karl Worthmann

We propose a scalable, policy-centric framework for continuous-time multi-asset portfolio-consumption optimization under inequality constraints. Our method integrates neural policies with Pontryagin's Maximum Principle (PMP) and enforces…

Portfolio Management · Quantitative Finance 2025-11-07 Jeonggyu Huh , Jaegi Jeon , Hyeng Keun Koo , Byung Hwa Lim

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang

We develop a model selection approach to tackle reinforcement learning with adversarial corruption in both transition and reward. For finite-horizon tabular MDPs, without prior knowledge on the total amount of corruption, our algorithm…

Machine Learning · Computer Science 2024-12-31 Chen-Yu Wei , Christoph Dann , Julian Zimmert

This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel and stochastic reward and cost functions. We propose a…

Machine Learning · Computer Science 2024-10-15 Kihyun Yu , Duksang Lee , William Overman , Dabeen Lee

We present an algorithm, based on the Differential Dynamic Programming framework, to handle trajectory optimization problems in which the horizon is determined online rather than fixed a priori. This algorithm exhibits exact one-step…

Robotics · Computer Science 2021-11-18 Kyle Stachowicz , Evangelos A. Theodorou

Long horizon lengths in Moving Horizon Estimation are desirable to reach the performance limits of the full information estimator. However, the conventional MHE technique suffers from a number of deficiencies in this respect. First, the…

Systems and Control · Computer Science 2014-02-17 Ali Al-Matouq , Tyrone Vincent

We prove that under five minimal axioms -- multi-dimensional quality, finite evaluation, effective optimization, resource finiteness, and combinatorial interaction -- any optimized AI agent will systematically under-invest effort in quality…

Artificial Intelligence · Computer Science 2026-03-31 Jiacheng Wang , Jinbin Huang

We provide a solution to the problem of receding horizon control for stochastic discrete-time systems with bounded control inputs and imperfect state measurements. For a suitable choice of control policies, we show that the finite-horizon…

Optimization and Control · Mathematics 2010-04-15 Peter Hokayem , Eugenio Cinquemani , Debasish Chatterjee , Federico Ramponi , John Lygeros

Bandit Convex Optimization (BCO) is a fundamental framework for modeling sequential decision-making with partial information, where the only feedback available to the player is the one-point or two-point function values. In this paper, we…

Machine Learning · Computer Science 2020-07-07 Peng Zhao , Guanghui Wang , Lijun Zhang , Zhi-Hua Zhou

For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact…

Machine Learning · Computer Science 2017-05-31 Joshua Achiam , David Held , Aviv Tamar , Pieter Abbeel

Episodic reinforcement learning and contextual bandits are two widely studied sequential decision-making problems. Episodic reinforcement learning generalizes contextual bandits and is often perceived to be more difficult due to long…

Machine Learning · Computer Science 2021-07-01 Zihan Zhang , Xiangyang Ji , Simon S. Du