English
Related papers

Related papers: Neural Co-state Policies: Structuring Hidden State…

200 papers

Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward…

Machine Learning · Computer Science 2021-03-16 Rui Zhao , Yang Gao , Pieter Abbeel , Volker Tresp , Wei Xu

Using historical data to predict future events has many applications in the real world, such as stock price prediction; the robot localization. In the past decades, the Convolutional long short-term memory (LSTM) networks have achieved…

Machine Learning · Computer Science 2022-12-20 Dexun Li

Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long…

Machine Learning · Computer Science 2024-10-29 Steven Morad , Chris Lu , Ryan Kortvelesy , Stephan Liwicki , Jakob Foerster , Amanda Prorok

In this paper, we present a novel reinforcement learning framework designed to optimize molecular dynamics by focusing on the entire trajectory rather than just the final molecular configuration. Leveraging a stochastic version of…

Optimization and Control · Mathematics 2024-10-22 Chandrajit Bajaj , Minh Nguyen , Conrad Li

We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Such restriction may…

Machine Learning · Computer Science 2023-04-07 Peter C. Y. Chen

We propose an iterative approach for designing Robust Learning Model Predictive Control (LMPC) policies for a class of nonlinear systems with additive, unmodelled dynamics. The nominal dynamics are assumed to be difference flat, i.e., the…

Systems and Control · Electrical Eng. & Systems 2023-03-23 Siddharth H. Nair , Francesco Borrelli

Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When…

Machine Learning · Computer Science 2021-11-19 Riad Akrour , Davide Tateo , Jan Peters

Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies, enabling market makers to optimize decision-making policies based on interactions with the limit order book environment. This…

Trading and Market Microstructure · Quantitative Finance 2026-02-17 Rafael Zimmer , Oswaldo Luiz do Valle Costa

Unsupervised learning of compact and relevant state representations has been proved very useful at solving complex reinforcement learning tasks. In this paper, we propose a recurrent capsule network that learns such representations by…

Machine Learning · Computer Science 2019-02-25 Louis Annabi , Michael Garcia Ortiz

Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement…

Systems and Control · Electrical Eng. & Systems 2025-03-20 Dongdong Li , Jiuxiang Dong

The computational properties of neural systems are often thought to be implemented in terms of their network dynamics. Hence, recovering the system dynamics from experimentally observed neuronal time series, like multiple single-unit (MSU)…

Neurons and Cognition · Quantitative Biology 2017-07-05 Daniel Durstewitz

We propose a stronger formulation of RL on top of RWKV-style recurrent sequence models, in which the fixed-size recurrent state is explicitly interpreted as a belief state rather than an opaque hidden vector. Instead of conditioning policy…

Machine Learning · Computer Science 2026-04-14 Liu Xiao

We study data-driven learning of robust stochastic control for infinite-horizon systems with potentially continuous state and action spaces. In many managerial settings--supply chains, finance, manufacturing, services, and dynamic…

Machine Learning · Statistics 2025-11-18 Shengbo Wang , Jason Meng , Nian Si , Jose Blanchet , Zhengyuan Zhou

In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial…

Machine Learning · Computer Science 2020-06-16 Rui Zhao , Yang Gao , Pieter Abbeel , Volker Tresp , Wei Xu

Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces. However, current models are limited to fully observable domains. In this paper, we describe a deep active…

Machine Learning · Computer Science 2021-02-08 Otto van der Himst , Pablo Lanillos

Solving partially observable Markov decision processes (POMDPs) remains a fundamental challenge in reinforcement learning (RL), primarily due to the curse of dimensionality induced by the non-stationarity of optimal policies. In this work,…

Optimization and Control · Mathematics 2025-10-20 Semih Cayci , Atilla Eryilmaz

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful…

Machine Learning · Computer Science 2025-12-08 Douglas Aberdeen , Jonathan Baxter

Recurrent neural networks (RNNs) have emerged as an effective representation of control policies in sequential decision-making problems. However, a major drawback in the application of RNN-based policies is the difficulty in providing…

Artificial Intelligence · Computer Science 2020-02-14 Steven Carr , Nils Jansen , Ufuk Topcu

We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using…

Machine Learning · Computer Science 2026-04-02 Philip Jordan , Maryam Kamgarpour

The standard approach for Partially Observable Markov Decision Processes (POMDPs) is to convert them to a fully observed belief-state MDP. However, the belief state depends on the system model and is therefore not viable in reinforcement…

Machine Learning · Computer Science 2024-10-30 Amit Sinha , Matthieu Geist , Aditya Mahajan