English
Related papers

Related papers: Learning with Options that Terminate Off-Policy

200 papers

This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While recent approaches like Proximal Policy Optimization (PPO)…

Computation and Language · Computer Science 2025-02-26 Bohan Zhang , Yixin Wang , Paramveer S. Dhillon

In experimenting with off-policy temporal difference (TD) methods in hierarchical reinforcement learning (HRL) systems, we have observed unwanted on-policy learning under reproducible conditions. Here we present modifications to several TD…

Machine Learning · Computer Science 2015-03-19 Mitchell Keith Bloch

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…

While on-policy algorithms are known for their stability, they often demand a substantial number of samples. In contrast, off-policy algorithms, which leverage past experiences, are considered sample-efficient but tend to exhibit…

Machine Learning · Computer Science 2023-09-28 Jianfei Ma

Soft Q-learning has emerged as a versatile model-free method for entropy-regularised reinforcement learning, optimising for returns augmented with a penalty on the divergence from a reference policy. Despite its success, the multi-step…

Machine Learning · Computer Science 2026-04-16 Pranav Mahajan , Ben Seymour

Time-constrained decision processes have been ubiquitous in many fundamental applications in physics, biology and computer science. Recently, restart strategies have gained significant attention for boosting the efficiency of…

Machine Learning · Computer Science 2020-07-02 Semih Cayci , Atilla Eryilmaz , R. Srikant

Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining…

Artificial Intelligence · Computer Science 2017-09-13 Denis Steckelmacher , Diederik M. Roijers , Anna Harutyunyan , Peter Vrancx , Hélène Plisnier , Ann Nowé

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

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Machine Learning · Computer Science 2020-08-12 Omer Gottesman , Joseph Futoma , Yao Liu , Sonali Parbhoo , Leo Anthony Celi , Emma Brunskill , Finale Doshi-Velez

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Machine Learning · Computer Science 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…

Artificial Intelligence · Computer Science 2026-05-26 Hong Su

Timing decisions are common: when to file your taxes, finish a referee report, or complete a task at work. We ask whether time preferences can be inferred when \textsl{only} task completion is observed. To answer this question, we analyze…

Theoretical Economics · Economics 2019-05-13 Paul Heidhues , Philipp Strack

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience,…

Machine Learning · Computer Science 2019-03-21 Kate Rakelly , Aurick Zhou , Deirdre Quillen , Chelsea Finn , Sergey Levine

Applying Q-learning to high-dimensional or continuous action spaces can be difficult due to the required maximization over the set of possible actions. Motivated by techniques from amortized inference, we replace the expensive maximization…

Machine Learning · Computer Science 2020-01-23 Tom Van de Wiele , David Warde-Farley , Andriy Mnih , Volodymyr Mnih

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks. Skill learning offers one way of identifying these regularities by decomposing pre-collected…

Machine Learning · Computer Science 2022-12-12 Yiding Jiang , Evan Zheran Liu , Benjamin Eysenbach , Zico Kolter , Chelsea Finn

Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…

Machine Learning · Computer Science 2025-12-30 Adam Jelley , Trevor McInroe , Sam Devlin , Amos Storkey

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…

Artificial Intelligence · Computer Science 2019-10-02 Hardik Meisheri , Vinita Baniwal , Nazneen N Sultana , Balaraman Ravindran , Harshad Khadilkar

This paper is concerned with the linear quadratic optimal control of discrete-time time-varying system with terminal state constraint. The main contribution is to propose a Q-learning algorithm for the optimal controller when the…

Optimization and Control · Mathematics 2023-07-20 Juanjuan Xu , Jingmei Liu , Zhaorong Zhang , Wei Wang

Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the online deployment. However, during the real-time serving, we observe varieties of interventions and constraints that cause inconsistency between the…

Machine Learning · Computer Science 2022-03-01 Da Xu , Yuting Ye , Chuanwei Ruan , Bo Yang