In the future we can expect that artificial intelligent agents, once deployed, will be required to learn continually from their experience during their operational lifetime. Such agents will also need to communicate with humans and other agents regarding the content of their experience, in the context of passing along their learnings, for the purpose of explaining their actions in specific circumstances or simply to relate more naturally to humans concerning experiences the agent acquires that are not necessarily related to their assigned tasks. We argue that to support these goals, an agent would benefit from an episodic memory; that is, a memory that encodes the agent's experience in such a way that the agent can relive the experience, communicate about it and use its past experience, inclusive of the agents own past actions, to learn more effective models and policies. In this short paper, we propose one potential approach to provide an AI agent with such capabilities. We draw upon the ever-growing body of work examining the function and operation of the Medial Temporal Lobe (MTL) in mammals to guide us in adding an episodic memory capability to an AI agent composed of artificial neural networks (ANNs). Based on that, we highlight important aspects to be considered in the memory organization and we propose an architecture combining ANNs and standard Computer Science techniques for supporting storage and retrieval of episodic memories. Despite being initial work, we hope this short paper can spark discussions around the creation of intelligent agents with memory or, at least, provide a different point of view on the subject.
Federal University of Technology - Paraná (UTFPR)（巴拉那联邦理工大学）
An intelligent agent may in general pursue multiple procedural goals simultaneously, which may lead to arise some conflicts (incompatibilities) among them. In this paper, we focus on the incompatibilities that emerge due to resources limitations. Thus, the contribution of this article is twofold. On one hand, we give an algorithm for identifying resource incompatibilities from a set of pursued goals and, on the other hand, we propose two ways for selecting those goals that will continue to be pursued: (i) the first is based on abstract argumentation theory, and (ii) the second based on two alg…
Federal University of Technology - Paraná (UTFPR)（巴拉那联邦理工大学）
During the first step of practical reasoning, i.e. deliberation or goals selection, an intelligent agent generates a set of pursuable goals and then selects which of them he commits to achieve. Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions. In the context of goals selection, agents should be able to explain the reasoning path that leads them to select (or not) a certain goal. In this article, we use an argumentation-based approach for generating explanations about that reasoning path. Besides, we aim to enrich …
Episodic-to-Semantic Consolidation Without Identity Drift
School of Software, Harbin Institute of Technology（哈尔滨工业大学软件学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；School of Future Science and Engineering, Soochow University（苏州大学未来科学与工程学院）
Federal University of Technology - Paraná (UTFPR)（巴拉那联邦理工大学）
Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions, behaviours and reasoning that produce their choices to the humans (or other systems) with which they interact. In this paper, we focus on how an extended model of BDI (Beliefs-Desires-Intentions) agents can be able to generate explanations about their reasoning, specifically, about the goals he decides to commit to. Our proposal is based on argumentation theory, we use arguments to represent the reasons that lead an agent to make a decision and use argumentation se…
Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Université de Lorraine（洛林大学）；Imperial College London（帝国理工学院）
The recently introduced Intelligent Trial and Error algorithm (IT\&E) enables robots to creatively adapt to damage in a matter of minutes by combining an off-line evolutionary algorithm and an on-line learning algorithm based on Bayesian Optimization. We extend the IT\&E algorithm to allow for robots to learn to compensate for damages while executing their task(s). This leads to a semi-episodic learning scheme that increases the robot's lifetime autonomy and adaptivity. Preliminary experiments on a toy simulation and a 6-legged robot locomotion task show promising results.
Federal University of ABC（ABC联邦大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Heriot-Watt University（赫瑞-瓦特大学）
This paper describes a competition proposal for evolving Intelligent Agents for the game-playing framework called EvoMan. The framework is based on the boss fights of the game called Mega Man II developed by Capcom. For this particular competition, the main goal is to beat all of the eight bosses using a generalist strategy. In other words, the competitors should train the agent to beat a set of the bosses and then the agent will be evaluated by its performance against all eight bosses. At the end of this paper, the competitors are provided with baseline results so that they can have an intuit…
Norweigan University of Science and Technology（挪威科技大学）；SINTEF Digital（SINTEF数字研究所）；Oklahoma State University（俄克拉荷马州立大学）
In this article, we explore the feasibility of applying proximal policy optimization, a state-of-the-art deep reinforcement learning algorithm for continuous control tasks, on the dual-objective problem of controlling an underactuated autonomous surface vehicle to follow an a priori known path while avoiding collisions with non-moving obstacles along the way. The artificial intelligent agent, which is equipped with multiple rangefinder sensors for obstacle detection, is trained and evaluated in a challenging, stochastically generated simulation environment based on the OpenAI gym python toolki…
Federal University of Technology - Paraná (UTFPR)（巴拉那联邦理工大学）；Umeå University（于默奥大学）；Artificial Intelligence Research Institute (IIIA-CSIC)（人工智能研究所）
During the first step of practical reasoning, i.e. deliberation, an intelligent agent generates a set of pursuable goals and then selects which of them he commits to achieve. An intelligent agent may in general generate multiple pursuable goals, which may be incompatible among them. In this paper, we focus on the definition, identification and resolution of these incompatibilities. The suggested approach considers the three forms of incompatibility introduced by Castelfranchi and Paglieri, namely the terminal incompatibility, the instrumental or resources incompatibility and the superfluity. W…
This paper proposes a framework for the biological learning mechanism as a general learning system. The proposal is as follows. The bursting and tonic modes of firing patterns found in many neuron types in the brain correspond to two separate modes of information processing, with one mode resulting in awareness, and another mode being subliminal. In such a coding scheme, a neuron in bursting state codes for the highest level of perceptual abstraction representing a pattern of sensory stimuli, or volitional abstraction representing a pattern of muscle contraction sequences. Within the 50-250 ms…
Cartheur Robotics, spol. s r.o.（Cartheur Robotics 公司）
Although the problem of a critique of robotic behavior in near-unanimous agreement to human norms seems intractable, a starting point of such an ambition is a framework of the collection of knowledge a priori and experience a posteriori categorized as a set of synthetical judgments available to the intelligence, translated into computer code. If such a proposal were successful, an algorithm with ethically traceable behavior and cogent equivalence to human cognition is established. This paper will propose the application of Kant's critique of reason to current programming constructs of an auton…
University of Innsbruck（因斯布鲁克大学）；University of Konstanz（康斯坦茨大学）
Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory. The model has been shown to provide a flexible framework for constructing reinforcement-learning agents, and it allows for quantum mechanical generalization, which leads to a speed-up in deliberation time. PS agents have been applied successfully in the context of complex skill learning in robotics, and in the design of state-of-the-art quantum experiments. In this paper, we study the performance of projective simulation in two benchmarking problems in navigation, namely …
Imperial College London（帝国理工学院）；Emotech Labs（Emotech实验室）；Leverhulme Centre for the Future of Intelligence（利弗休姆未来智能中心）；University College London（伦敦大学学院）
In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either unnecessary, or worse, accumulating prediction error. In contrast, intelligent behaviour in biological organisms is characterised by the ability to plan over varying temporal scales depending on the context. Inspired by the recent works on human time perception, we devise a novel approach to learning a transition dynamics model, based on the sequences of episodic memo…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of Waterloo（滑铁卢大学）
Recent work has suggested reducing electricity generation cost by cutting the peak to average ratio (PAR) without reducing the total amount of the loads. However, most of these proposals rely on consumer's willingness to act. In this paper, we propose an approach to cut PAR explicitly from the supply side. The resulting cut loads are then distributed among consumers by the means of a multiunit auction which is done by an intelligent agent on behalf of the consumer. This approach is also in line with the future vision of the smart grid to have the demand side matched with the supply side. Exper…
Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI
Kansas State University（堪萨斯州立大学）；University of Louisville（路易斯维尔大学）
This paper presents a novel approach to the technical analysis of wireheading in intelligent agents. Inspired by the natural analogues of wireheading and their prevalent manifestations, we propose the modeling of such phenomenon in Reinforcement Learning (RL) agents as psychological disorders. In a preliminary step towards evaluating this proposal, we study the feasibility and dynamics of emergent addictive policies in Q-learning agents in the tractable environment of the game of Snake. We consider a slightly modified settings for this game, in which the environment provides a "drug" seed alon…
InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis
School of Physics and Astronomy, The University of Edinburgh（物理学与天文学学院，爱丁堡大学）；Glasgow College, University of Electronic Science and Technology of China（电子科技大学成都学院）；School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China（机械与电子工程学院，电子科技大学）；Department of Systems Engineering, City University of Hong Kong（系统工程系，香港城市大学）
The field of user experience (UX) based on the design philosophy of "user-centered design" is moving towards the intelligence era. Still, the existing UX paradigm mainly aims at non-intelligent systems and lacks a systematic approach to UX for intelligent systems. Throughout the development of UX, the UX paradigm shows the evolution characteristics of the cross-technology era. At present, the intelligence era has put forward new demands on the UX paradigm. For this reason, this paper proposes a "UX 3.0" paradigm framework and the corresponding UX methodology system in the intelligence era. The…
