اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدAplib: Tactical Programming of Intelligent Agents
46
0
0.0
(
0
)
تأليف
I. S. W. B. Prasetya
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
This paper presents aplib, a Java library for programming intelligent agents, featuring BDI and multi agency, but adding on top of it a novel layer of tactical programming inspired by the domain of theorem proving. Aplib is also implemented in such a way to provide the fluency of a Domain Specific Language (DSL). Compared to dedicated BDI agent programming languages such as JASON, 2APL, or GOAL,aplibs embedded DSL approach does mean that aplib programmers will still be limited by Java syntax, but on other hand they get all the advantages that Java programmers get: rich language features (object orientation, static type checking, $lambda$-expression, libraries, etc), a whole array of development tools, integration with other technologies, large community, etc.
قيم البحث
اقرأ أيضاً
The most advanced implementation of adaptive constraint processing with Constraint Handling Rules (CHR) allows the application of intelligent search strategies to solve Constraint Satisfaction Problems (CSP). This presentation compares an improved ve
rsion of conflict-directed backjumping and two variants of dynamic backtracking with respect to chronological backtracking on some of the AIM instances which are a benchmark set of random 3-SAT problems. A CHR implementation of a Boolean constraint solver combined with these different search strategies in Java is thus being compared with a CHR implementation of the same Boolean constraint solver combined with chronological backtracking in SICStus Prolog. This comparison shows that the addition of ``intelligence to the search process may reduce the number of search steps dramatically. Furthermore, the runtime of their Java implementations is in most cases faster than the implementations of chronological backtracking. More specifically, conflict-directed backjumping is even faster than the SICStus Prolog implementation of chronological backtracking, although our Java implementation of CHR lacks the optimisations made in the SICStus Prolog system. To appear in Theory and Practice of Logic Programming (TPLP).
Building on ideas from probabilistic programming, we introduce the concept of an expectation programming framework (EPF) that automates the calculation of expectations. Analogous to a probabilistic program, an expectation program is comprised of a mi
x of probabilistic constructs and deterministic calculations that define a conditional distribution over its variables. However, the focus of the inference engine in an EPF is to directly estimate the resulting expectation of the program return values, rather than approximate the conditional distribution itself. This distinction allows us to achieve substantial performance improvements over the standard probabilistic programming pipeline by tailoring the inference to the precise expectation we care about. We realize a particular instantiation of our EPF concept by extending the probabilistic programming language Turing to allow so-called target-aware inference to be run automatically, and show that this leads to significant empirical gains compared to conventional posterior-based inference.
Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol incentivises a
gents to behave Bayes-optimally. We empirically investigate this claim on a number of prediction and bandit tasks. Inspired by ideas from theoretical computer science, we show that meta-learned and Bayes-optimal agents not only behave alike, but they even share a similar computational structure, in the sense that one agent system can approximately simulate the other. Furthermore, we show that Bayes-optimal agents are fixed points of the meta-learning dynamics. Our results suggest that memory-based meta-learning might serve as a general technique for numerically approximating Bayes-optimal agents - that is, even for task distributions for which we currently dont possess tractable models.
We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to o
bjects that were not referenced during training. The agents develop disentangled interpretable representations that allow them to generalize to a wide variety of zero-shot semantic tasks.
For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by the system
designer. We highlight some ways that misspecification can occur and discuss some behavioural issues that could arise from misspecification, including deceptive or manipulative language, and review some approaches for avoiding these issues.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
