Topic Tag: game

home Forums Topic Tag: game

 Symbolic LTLf Synthesis

LTLf synthesis is the process of finding a strategy that satisfies a linear temporal specification over finite traces. An existing solution to this problem relies on a reduction to a DFA game. In this paper, we propose a symbolic framework for LTLf synthesis based on this technique, by performing t…


 Behavior Trees in Robotics and AI: An Introduction

A Behavior Tree (BT) is a way to structure the switching between different tasks in an autonomous agent, such as a robot or a virtual entity in a computer game. BTs are a very efficient way of creating complex systems that are both modular and reactive. These properties are crucial in many applicat…


 Cost Adaptation for Robust Decentralized Swarm Behaviour

The multi-agent swarm system is a robust paradigm which can drive efficient completion of complex tasks even under energy limitations and time constraints. However, coordination of a swarm from a centralized command center can be difficult, particularly as the swarm becomes large and spans wide ran…


 Learning to Design Games: Strategic Environments in Deep Reinforcement Learning

  

In typical reinforcement learning (RL), the environment is assumed given and the goal of the learning is to identify an optimal policy for the agent taking actions through its interactions with the environment. In this paper, we extend this setting by considering the environment is not given, but c…


 Multi-Generator Generative Adversarial Nets

  

We propose in this paper a novel approach to address the mode collapse problem in Generative Adversarial Nets (GANs) by training many generators. The training procedure is formulated as a minimax game among many generators, a classifier, and a discriminator. Generators produce data to fool the disc…


 Embodied Artificial Intelligence through Distributed Adaptive Control: An Integrated Framework

  

In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances of the field. Regarding integration, we note that the most impactful recent contributions have been made possible t…


 Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

 

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community,…


 The Uncertainty Bellman Equation and Exploration

  

We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar uncertainty Bellman equation (UBE), which …


 Dynamic Pricing in Competitive Markets

 

Dynamic pricing of goods in a competitive environment to maximize revenue is a natural objective and has been a subject of research over the years. In this paper, we focus on a class of markets exhibiting the substitutes property with sellers having divisible and replenishable goods. Depending on t…


 Shared Learning : Enhancing Reinforcement in Q-Ensembles

  

Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that require a large amount of data to train in order to obtain resu…


 Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as a case study, wh…


 Guiding Reinforcement Learning Exploration Using Natural Language

  

In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and st…


 Towards personalized human AI interaction – adapting the behavior of AI agents using neural signatures of subjective interest

  

Reinforcement Learning AI commonly uses reward/penalty signals that are objective and explicit in an environment — e.g. game score, completion time, etc. — in order to learn the optimal strategy for task performance. However, Human-AI interaction for such AI agents should include additi…


 HitFraud: A Broad Learning Approach for Collective Fraud Detection in Heterogeneous Information Networks

On electronic game platforms, different payment transactions have different levels of risk. Risk is generally higher for digital goods in e-commerce. However, it differs based on product and its popularity, the offer type (packaged game, virtual currency to a game or subscription service), storefro…


 Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning

   

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from t…


 Dual Discriminator Generative Adversarial Nets

    

We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and re…


 Combining Strategic Learning and Tactical Search in Real-Time Strategy Games

 

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 suffer due to lost details. A competing method is to sample …


 Hamiltonian Maker-Breaker games on small graphs

We look at the unbiased Maker-Breaker Hamiltonicity game played on the edge set of a complete graph $K_n$, where Maker’s goal is to claim a Hamiltonian cycle. First, we prove that, independent of who starts, Maker can win the game for $n = 8$ and $n = 9$. Then we use an inductive argument to …


 Prosocial learning agents solve generalized Stag Hunts better than selfish ones

 

There is much interest in applying reinforcement learning methods to multi-agent systems. A popular way to do so is the method of reactive training — ie. treating other agents as if they are a stationary part of the learner’s environment. Dyads of such learners, if they converge, will c…


 Uncertainty measurement with belief entropy on interference effect in Quantum-Like Bayesian Networks

 

Social dilemmas have been regarded as the essence of evolution game theory, in which the prisoner’s dilemma game is the most famous metaphor for the problem of cooperation. Recent findings revealed people’s behavior violated the Sure Thing Principle in such games. Classic probability me…


 Evolution Strategies as a Scalable Alternative to Reinforcement Learning

 

We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the…


 A multi-agent reinforcement learning model of common-pool resource appropriation

  

Humanity faces numerous problems of common-pool resource appropriation. This class of multi-agent social dilemma includes the problems of ensuring sustainable use of fresh water, common fisheries, grazing pastures, and irrigation systems. Abstract models of common-pool resource appropriation based …


 Active Exploration for Learning Symbolic Representations

 

We introduce an online active exploration algorithm for data-efficiently learning an abstract symbolic model of an environment. Our algorithm is divided into two parts: the first part quickly generates an intermediate Bayesian symbolic model from the data that the agent has collected so far, which …


 Knowledge Sharing for Reinforcement Learning: Writing a BOOK

 

This paper proposes a novel deep reinforcement learning (RL) method integrating the neural-network-based RL and the classical RL based on dynamic programming. In comparison to the conventional deep RL methods, our method enhances the convergence speed and the performance by delving into the followi…


 The Pragmatics of Indirect Commands in Collaborative Discourse

 

Today’s artificial assistants are typically prompted to perform tasks through direct, imperative commands such as emph{Set a timer} or emph{Pick up the box}. However, to progress toward more natural exchanges between humans and these assistants, it is important to understand the way non-imper…