English
Related papers

Related papers: Incremental Data-Driven Policy Synthesis via Game …

200 papers

Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning. In this work, we study joint temporal and state abstraction in reinforcement learning, where temporally-extended…

Machine Learning · Computer Science 2022-06-09 Dongge Han , Sebastian Tschiatschek

This paper is concerned with a compositional approach for constructing both infinite (reduced-order models) and finite abstractions (a.k.a. finite Markov decision processes (MDPs)) of large-scale interconnected discrete-time stochastic…

Systems and Control · Computer Science 2020-02-17 Abolfazl Lavaei , Sadegh Soudjani , Majid Zamani

We consider the policy synthesis problem for continuous-state controlled Markov processes evolving in discrete time, when the specification is given as a B\"uchi condition (visit a set of states infinitely often). We decompose computation…

Systems and Control · Electrical Eng. & Systems 2020-02-17 Rupak Majumdar , Kaushik Mallik , Sadegh Soudjani

While the utility of well-chosen abstractions for understanding and predicting the behaviour of complex systems is well appreciated, precisely what an abstraction $\textit{is}$ has so far has largely eluded mathematical formalization. In…

Artificial Intelligence · Computer Science 2021-06-29 Beren Millidge

We study the asymptotic optimality of abstraction-based control synthesis algorithms. Specifically, we consider uncertain MDP (UMDP) abstraction, and investigate whether refinement leads to optimal results, i.e., an optimal controller and…

Systems and Control · Electrical Eng. & Systems 2026-04-16 Ibon Gracia , Morteza Lahijanian

A major open problem in the area of infinite-duration games is to characterize winning conditions that are determined in finite-memory strategies. Infinite-duration games are usually studied over edge-colored graphs, with winning conditions…

Computer Science and Game Theory · Computer Science 2022-01-25 Alexander Kozachinskiy

A commonly used technique for managing AI complexity in real-time strategy (RTS) games is to use action and/or state abstractions. High-level abstractions can often lead to good strategic decision making, but tactical decision quality may…

Artificial Intelligence · Computer Science 2017-09-12 Nicolas A. Barriga , Marius Stanescu , Michael Buro

Synthesizing near-optimal mixed strategies for zero-sum differential games (ZSDGs) has been a longstanding challenge. Existing research mainly focuses on characterizing the theoretical value function, while the practical design of…

Optimization and Control · Mathematics 2026-05-13 Tao Xu , Wang Xi , Jianping He

We consider the problem of computing numerical invariants of programs by abstract interpretation. Our method eschews two traditional sources of imprecision: (i) the use of widening operators for enforcing convergence within a finite number…

Programming Languages · Computer Science 2015-05-27 Thomas Martin Gawlitza , David Monniaux

Making decisions in complex environments is a key challenge in artificial intelligence (AI). Situations involving multiple decision makers are particularly complex, leading to computational intractability of principled solution methods. A…

Artificial Intelligence · Computer Science 2021-03-02 Frans A. Oliehoek , Stefan Witwicki , Leslie P. Kaelbling

Faced with data-driven policies, individuals will manipulate their features to obtain favorable decisions. While earlier works cast these manipulations as undesirable gaming, recent works have adopted a more nuanced causal framing in which…

Machine Learning · Computer Science 2023-02-22 Tom Yan , Shantanu Gupta , Zachary Lipton

We present a novel approach for fast and reliable policy selection for navigation in partial maps. Leveraging the recent learning-augmented model-based Learning over Subgoals Planning (LSP) abstraction to plan, our robot reuses data…

Robotics · Computer Science 2024-01-10 Abhishek Paudel , Gregory J. Stein

This work investigates the formal policy synthesis of continuous-state stochastic dynamic systems given high-level specifications in linear temporal logic. To learn an optimal policy that maximizes the satisfaction probability, we take a…

Artificial Intelligence · Computer Science 2023-04-21 Lening Li , Zhentian Qian

As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignment and exploration become more challenging, and the long planning horizon hinders mode discovery…

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

Evolutionary games on graphs play an important role in the study of evolution of cooperation in applied biology. Using rigorous mathematical concepts from a dynamical systems and graph theoretical point of view, we formalize the notions of…

Dynamical Systems · Mathematics 2014-11-18 Jeremias Epperlein , Stefan Siegmund , Petr Stehlík

Analysis of Markov Decision Processes (MDP) is often hindered by state space explosion. Abstraction is a well-established technique in model checking to mitigate this issue. This paper presents a novel lazy abstraction method for MDP…

Logic in Computer Science · Computer Science 2024-06-04 Dániel Szekeres , Kristóf Marussy , István Majzik

Intensity control is a class of continuous-time dynamic optimization problems with many important applications in Operations Research including queueing and revenue management. In this study, we propose a practical continuous-time…

Machine Learning · Computer Science 2026-04-14 Huiling Meng , Ningyuan Chen , Xuefeng Gao

Strategy video games challenge AI agents with their combinatorial search space caused by complex game elements. State abstraction is a popular technique that reduces the state space complexity. However, current state abstraction methods for…

Artificial Intelligence · Computer Science 2022-05-31 Linjie Xu , Jorge Hurtado-Grueso , Dominic Jeurissen , Diego Perez Liebana , Alexander Dockhorn

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara
‹ Prev 1 4 5 6 7 8 10 Next ›