In this paper, we propose actor-director-critic, a new framework for deep reinforcement learning. Compared with the actor-critic framework, the director role is added, and action classification and action evaluation are applied simultaneously to improve the decision-making performance of the agent. Firstly, the actions of the agent are divided into high quality actions and low quality actions according to the rewards returned from the environment. Then, the director network is trained to have the ability to discriminate high and low quality actions and guide the actor network to reduce the repetitive exploration of low quality actions in the early stage of training. In addition, we propose an improved double estimator method to better solve the problem of overestimation in the field of reinforcement learning. For the two critic networks used, we design two target critic networks for each critic network instead of one. In this way, the target value of each critic network can be calculated by taking the average of the outputs of the two target critic networks, which is more stable and accurate than using only one target critic network to obtain the target value. In order to verify the performance of the actor-director-critic framework and the improved double estimator method, we applied them to the TD3 algorithm to improve the TD3 algorithm. Then, we carried out experiments in multiple environments in MuJoCo and compared the experimental data before and after the algorithm improvement. The final experimental results show that the improved algorithm can achieve faster convergence speed and higher total return.

Recent progress in logic programming (e.g., the development of the Answer Set Programming paradigm) has made it possible to teach it to general undergraduate and even middle/high school students. Given the limited exposure of these students to computer science, the complexity of downloading, installing and using tools for writing logic programs could be a major barrier for logic programming to reach a much wider audience. We developed onlineSPARC, an online answer set programming environment with a self contained file system and a simple interface. It allows users to type/edit logic programs and perform several tasks over programs, including asking a query to a program, getting the answer sets of a program, and producing a drawing/animation based on the answer sets of a program.

The paper presents a knowledge representation language $\mathcal{A}log$ which extends ASP with aggregates. The goal is to have a language based on simple syntax and clear intuitive and mathematical semantics. We give some properties of $\mathcal{A}log$, an algorithm for computing its answer sets, and comparison with other approaches.

Epistemic Specifications allow for the correct representation of incomplete information in the presence of multiple belief sets by expanding Answer Set Programming with modal operators $K$ and M. The meaning of M in the existing work does not correspond well to the principle of justifiedness accepted by the community. It is, however, challenging to characterize the justfiedness of each belief, due to the complexity introduced by M. We address this issue by identifying a belief set with a program which uniquely decides the belief set. This idea leads to a novel definition of the semantics of Epistemic Specifications which assures that each belief in any belief set is well justified.  We also show that conformant planning problems can be naturally represented by Epistemic Specification under our semantics.

This paper discusses the design of an introductory computer science course for high school students using declarative programming. Though not often taught at the K-12 level, declarative programming is a viable paradigm for teaching computer science due to its importance in artificial intelligence and in helping student explore and understand problem spaces. This paper describes the authors' implementation of a declarative programming course for high school students during a 4-week summer session.

Aspect extraction is a key task of fine-grained opinion mining. Although it has been studied by many researchers, it remains to be highly challenging. This paper proposes a novel unsupervised approach to make a major improvement. The approach is based on the framework of lifelong learning and is implemented with two forms of recommendations that are based on semantic similarity and aspect associations respectively. Experimental results using eight review datasets show the effectiveness of the proposed approach.

Recent progress in logic programming, particularly answer set programming, has enabled us to teach it to undergraduate and high school students. We developed an online answer set programming environment with simple interface and self contained file system. It is expected to make the teaching of answer set programming more effective and help us to reach more students.

Boolean SATisfiability (SAT) is an important problem in AI. SAT solvers have been effectively used in important industrial applications including automated planning and verification. In this paper, we present novel algorithms for fast SAT solving by employing two common subclause elimination (CSE) approaches. Our motivation is that modern SAT solving techniques can be more efficient on CSE-processed instances. Empirical study shows that CSE can significantly speed up SAT solving.

The paper presents a knowledge representation language $\mathcal{A}log$ which extends ASP with aggregates. The goal is to have a language based on simple syntax and clear intuitive and mathematical semantics. We give some properties of $\mathcal{A}log$, an algorithm for computing its answer sets, and comparison with other approaches.

Recently, a new language AC(C) was proposed to integrate answer set programming (ASP) and constraint logic programming (CLP). In this paper, we show that temporally expressive planning problems in PDDL2.1 can be translated into AC(C) and solved using AC(C) solvers. Compared with existing approaches, the new approach puts less restrictions on the planning problems and is easy to extend with new features like PDDL axioms. It can also leverage the inference engine for AC(C) which has the potential to exploit the best reasoning mechanisms developed in the ASP, SAT and CP communities.