English
Related papers

Related papers: Policy as Types

200 papers

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal…

Artificial Intelligence · Computer Science 2026-04-29 Simone Murari , Celeste Veronese , Daniele Meli

The theory of classical realizability is a framework for the Curry-Howard correspondence which enables to associate a program with each proof in Zermelo-Fraenkel set theory. But, almost all the applications of mathematics in physics,…

Logic in Computer Science · Computer Science 2023-06-22 Jean-Louis Krivine

This paper provides a call-by-name and a call-by-value term calculus, both of which have a Curry-Howard correspondence to the box fragment of the intuitionistic modal logic IK. The strong normalizability and the confluency of the calculi…

Logic in Computer Science · Computer Science 2016-06-17 Yoshihiko Kakutani

We describe a process calculus featuring high level constructs for component-oriented programming in a distributed setting. We propose an extension of the higher-order pi-calculus intended to capture several important mechanisms related to…

Programming Languages · Computer Science 2009-09-04 Daniel Hirschkoff , Aurélien Pardon , Tom Hirschowitz , Samuel Hym , Damien Pous

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…

Machine Learning · Computer Science 2020-06-16 Jun Song , Chaoyue Zhao

We explore recursive programming with extensible data types. Row types make the structure of data types first class, and can express a variety of type system features including record subtyping and combination of case branches. Our goal is…

Programming Languages · Computer Science 2025-07-23 Alex Hubers , Apoorv Ingle , Andrew Marmaduke , J. Garrett Morris

Classical decision theory models behaviour in terms of utility maximisation where utilities represent rational preference relations over outcomes. However, empirical evidence and theoretical considerations suggest that we need to go beyond…

Computer Science and Game Theory · Computer Science 2015-06-04 Jules Hedges , Paulo Oliva , Evguenia Sprits , Viktor Winschel , Philipp Zahn

Policy-Space Response Oracles (PSRO) is a general algorithmic framework for learning policies in multiagent systems by interleaving empirical game analysis with deep reinforcement learning (Deep RL). At each iteration, Deep RL is invoked to…

Multiagent Systems · Computer Science 2021-06-04 Max Olan Smith , Thomas Anthony , Michael P. Wellman

We study encodings of the lambda-calculus into the pi-calculus in the unexplored case of calculi with non-determinism and failures. On the sequential side, we consider lambdafail, a new non-deterministic calculus in which intersection types…

Logic in Computer Science · Computer Science 2024-02-14 Joseph W. N. Paulus , Daniele Nantes-Sobrinho , Jorge A. Pérez

The complexity of large-scale distributed systems, particularly when deployed in physical space, calls for new mechanisms to address composability and reusability of collective adaptive behaviour. Computational fields have been proposed as…

Logic in Computer Science · Computer Science 2019-01-15 Mirko Viroli , Giorgio Audrito , Ferruccio Damiani , Danilo Pianini , Jacob Beal

High-dimensional policies, such as those represented by neural networks, cannot be reasonably interpreted by humans. This lack of interpretability reduces the trust users have in policy behavior, limiting their use to low-impact tasks such…

Machine Learning · Computer Science 2021-09-20 John Mern , Sidhart Krishnan , Anil Yildiz , Kyle Hatch , Mykel J. Kochenderfer

The treatment of equality as a type in type theory gives rise to an interesting type-theoretic structure known as `identity type'. The idea is that, given terms $a,b$ of a type $A$, one may form the type $Id_{A}(a,b)$, whose elements are…

Logic in Computer Science · Computer Science 2018-04-27 Arthur Freitas Ramos , Ruy J. G. B. de Queiroz , Anjolina G. de Oliveira

We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain…

Machine Learning · Computer Science 2017-06-23 Stephan Zheng , Yisong Yue , Patrick Lucey

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We…

Artificial Intelligence · Computer Science 2016-12-06 Pierre-Luc Bacon , Jean Harb , Doina Precup

Modeling multimodal human behavior has been a key barrier to increasing the level of interaction between human and robot, particularly for collaborative tasks. Our key insight is that an effective, learned robot policy used for human-robot…

Robotics · Computer Science 2023-11-14 Eley Ng , Ziang Liu , Monroe Kennedy

We derive recursive equations for the characteristic numbers of rational nodal plane curves with at most one cusp, subject to point conditions, tangent conditions and flag conditions, developing techniques akin to quantum cohomology on a…

alg-geom · Mathematics 2016-08-15 Lars Ernström , Gary Kennedy

Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through…

Machine Learning · Computer Science 2025-01-22 Chuning Zhu , Xinqi Wang , Tyler Han , Simon S. Du , Abhishek Gupta

Learning options that allow agents to exhibit temporally higher order behavior has proven to be useful in increasing exploration, reducing sample complexity and for various transfer scenarios. Deep Discovery of Options (DDO) is a generative…

Machine Learning · Computer Science 2019-08-06 Ameet Deshpande , Harshavardhan Kamarthi , Balaraman Ravindran

Generalising slightly the notions of a strict computability model and of a simulation between them, which were elaborated by Longley and Normann, we define canonical computability models over categories and appropriate Set-valued functors…

Category Theory · Mathematics 2021-05-17 Iosif Petrakis

Potential heuristics for state-space search are defined as weighted sums over simple state features. Atomic features consider the value of a single state variable in a factored state representation, while binary features consider joint…

Artificial Intelligence · Computer Science 2019-09-27 Florian Pommerening , Malte Helmert , Blai Bonet