English
Related papers

Related papers: Dyna-Style Planning with Linear Function Approxima…

200 papers

Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement real trajectories, or sequences of sampled states over time, with simulated ones sampled from a…

Machine Learning · Computer Science 2018-05-28 Ryan Faulkner , Doina Precup

Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one-step experience to update the action-value function. This…

Artificial Intelligence · Computer Science 2018-06-13 Yangchen Pan , Muhammad Zaheer , Adam White , Andrew Patterson , Martha White

We study how a Reinforcement Learning (RL) system can remain sample-efficient when learning from an imperfect model of the environment. This is particularly challenging when the learning system is resource-constrained and in continual…

Machine Learning · Computer Science 2024-07-01 Bradley Burega , John D. Martin , Luke Kapeluck , Michael Bowling

We study query and computationally efficient planning algorithms with linear function approximation and a simulator. We assume that the agent only has local access to the simulator, meaning that the agent can only query the simulator at…

Machine Learning · Computer Science 2022-02-08 Dong Yin , Botao Hao , Yasin Abbasi-Yadkori , Nevena Lazić , Csaba Szepesvári

During sleep and awake rest, the hippocampus replays sequences of place cells that have been activated during prior experiences. These have been interpreted as a memory consolidation process, but recent results suggest a possible…

Artificial Intelligence · Computer Science 2018-08-14 Lise Aubin , Mehdi Khamassi , Benoît Girard

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

This paper analyzes multi-step TD-learning algorithms within the `deadly triad' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that n-step TD-learning algorithms…

Systems and Control · Electrical Eng. & Systems 2024-04-09 Donghwan Lee

Learning-based approaches are increasingly popular for traffic control problems. However, these approaches are applied typically as black boxes with limited theoretical guarantees and interpretability. In this paper, we consider the theory…

Systems and Control · Electrical Eng. & Systems 2024-04-16 Yidan Wu , Jianan Zhang , Li Jin

We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned…

Machine Learning · Computer Science 2019-02-05 Norman Tasfi , Miriam Capretz

Dyna is a fundamental approach to model-based reinforcement learning (MBRL) that interleaves planning, acting, and learning in an online setting. In the most typical application of Dyna, the dynamics model is used to generate one-step…

Artificial Intelligence · Computer Science 2019-04-01 G. Zacharias Holland , Erin J. Talvitie , Michael Bowling

This paper analyzes multi-step temporal difference (TD)-learning algorithms within the ``deadly triad'' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that $n$-step…

Machine Learning · Computer Science 2026-02-24 Han-Dong Lim , Donghwan Lee

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

We consider local planning in fixed-horizon MDPs with a generative model under the assumption that the optimal value function lies close to the span of a feature map. The generative model provides a local access to the MDP: The planner can…

Machine Learning · Computer Science 2021-07-12 Gellért Weisz , Philip Amortila , Barnabás Janzer , Yasin Abbasi-Yadkori , Nan Jiang , Csaba Szepesvári

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

Machine Learning · Computer Science 2024-06-04 Guillermo Infante , David Kuric , Anders Jonsson , Vicenç Gómez , Herke van Hoof

Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple,…

Machine Learning · Computer Science 2022-12-22 Michael Janner , Yilun Du , Joshua B. Tenenbaum , Sergey Levine

The paper is devoted to the study of a new class of optimal control problems governed by discontinuous constrained differential inclusions of the sweeping type with involving the duration of the dynamic process into optimization. We develop…

Optimization and Control · Mathematics 2023-10-18 Giovanni Colombo , Boris S. Mordukhovich , Dao Nguyen , Trang Nguyen

Imitation learning is a control design paradigm that seeks to learn a control policy reproducing demonstrations from expert agents. By substituting expert demonstrations for optimal behaviours, the same paradigm leads to the design of…

Machine Learning · Computer Science 2024-12-20 Dharmesh Tailor , Dario Izzo

Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is…

Artificial Intelligence · Computer Science 2013-01-14 Harm van Seijen , Richard S. Sutton

The paper focuses on mean-field type multi-agent control problems with finite state and action spaces where the dynamics and cost structures are symmetric and homogeneous, and are affected by the distribution of the agents. A standard…

Optimization and Control · Mathematics 2025-07-03 Erhan Bayraktar , Ali D. Kara

In this paper, we propose a sampling-based planning and optimal control method of nonlinear systems under non-differentiable constraints. Motivated by developing scalable planning algorithms, we consider the optimal motion plan to be a…

Systems and Control · Computer Science 2016-12-19 Jie Fu
‹ Prev 1 2 3 10 Next ›