We consider multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents can be brittle because they can overfit their training partners' policies. This overfitting can produce agents that adopt policies that act under the expectation that other agents will act in a certain way rather than react to their actions. Our objective is to bias the learning process towards finding reactive strategies towards other agents' behaviors. Our method, transfer empowerment, measures the potential influence between agents' actions. Results from three simulated cooperation scenarios support our hypothesis that transfer empowerment improves MARL performance. We discuss how transfer empowerment could be a useful principle to guide multi-agent coordination by ensuring reactiveness to one's partner.
Multi-Agent Empowerment and Emergence of Complex Behavior in Groups
Department of Physics, Department of Biology, Initiative in Theory and Modeling of Living Systems（物理系、生物学系、生命系统理论与建模倡议）；Department of Computer Science, School of Physics, Engineering and Computer Science（计算机科学系，物理、工程与计算机科学学院）
Mobile robot navigation has seen extensive research in the last decades. The aspect of collaboration with robots and humans sharing workspaces will become increasingly important in the future. Therefore, the next generation of mobile robots needs to be socially-compliant to be accepted by their human collaborators. However, a formal definition of compliance is not straightforward. On the other hand, empowerment has been used by artificial agents to learn complicated and generalized actions and also has been shown to be a good model for biological behaviors. In this paper, we go beyond the appr…
Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents. In literature, the term empowerment is used to represent the maximum of MIAS at a certain state. While empowerment has been shown to solve a broad range of reinforcement learning problems, its calculation in arbitrary dynamics is a challenging problem because it relies on the estimation of mutual information. Existing approaches, which rely on sampling, are …
Massachusetts Institute of Technology（麻省理工学院）；Horizon Robotics（地平线机器人）
In order to provide adaptive and user-friendly solutions to robotic manipulation, it is important that the agent can learn to accomplish tasks even if they are only provided with very sparse instruction signals. To address the issues reinforcement learning algorithms face when task rewards are sparse, this paper proposes an intrinsic motivation approach that can be easily integrated into any standard reinforcement learning algorithm and can allow robotic manipulators to learn useful manipulation skills with only sparse extrinsic rewards. Through integrating and balancing empowerment and curios…
Towards Empowerment Gain through Causal Structure Learning in Model-Based RL
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；MBZUAI（Mohamed bin Zayed 人工智能大学）；University of Liverpool（利物浦大学）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-independent, intrinsic motivation to restructure the world. We show how changes in embodiment and in the environment change the resulting behaviour of the agent and the artefacts left in the world. For this purpose, we introduce an approximation of the established empowerment formalism based on sparse sampling, which is simpler and significantly faste…
The Alan Turing Institute（艾伦·图灵研究所）；University College London（伦敦大学学院）；University of Bologna（博洛尼亚大学）
Social dilemmas have been widely studied to explain how humans are able to cooperate in society. Considerable effort has been invested in designing artificial agents for social dilemmas that incorporate explicit agent motivations that are chosen to favor coordinated or cooperative responses. The prevalence of this general approach points towards the importance of achieving an understanding of both an agent's internal design and external environment dynamics that facilitate cooperative behavior. In this paper, we investigate how partner selection can promote cooperative behavior between agents …
University of Hertfordshire（赫特福德大学）；New York University（纽约大学）；University of London（伦敦大学）
Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards. Applications in video games are varied, and range from intrinsically motivated general game-playing agents to non-player characters such as companions and enemies. The information-theoretic quantity of Empowerment is a particularly promising candidate motivation to produce believable, generic and robust behaviour. However, while it can be used in the absence of external reward functions that would need to be crafted and learned, empowerment is computationally expensive. …
A key challenge in the study of multiagent cooperation is the need for individual agents not only to cooperate effectively, but to decide with whom to cooperate. This is particularly critical in situations when other agents have hidden, possibly misaligned motivations and goals. Social deduction games offer an avenue to study how individuals might learn to synthesize potentially unreliable information about others, and elucidate their true motivations. In this work, we present Hidden Agenda, a two-team social deduction game that provides a 2D environment for studying learning agents in scenari…
This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors. It quantifies how much influence and control an agent has over the world it can perceive. This book chapter discusses the general idea behind empowerment as an intrinsic motivation and showcases several previous applications of empowerment to demonstrate how empowerment can be applied to different sensor-motor configuration, and how the same formalism can lead to differe…
Although there are many approaches to implement intrinsically motivated artificial agents, the combined usage of multiple intrinsic drives remains still a relatively unexplored research area. Specifically, we hypothesize that a mechanism capable of quantifying and controlling the evolution of the information flow between the agent and the environment could be the fundamental component for implementing a higher degree of autonomy into artificial intelligent agents. This paper propose a unified strategy for implementing two semantically orthogonal intrinsic motivations: curiosity and empowerment…
Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', which rewards the agent based on certain features of the current sensor state. An intrinsic reward function based on the principle of empowerment assigns rewards proportional to the amount of control the agent has over its own sensors. We implemented a variation on a recently proposed intrinsically motivated agent, which we refer to as the 'curious' agent, and an empowerment-ins…
One of the remarkable feats of intelligent life is that it restructures the world it lives in for its own benefit. This extended abstract outlines how the information-theoretic principle of empowerment, as an intrinsic motivation, can be used to restructure the environment an agent lives in. We present a first qualitative evaluation of how an agent in a 3d-gridworld builds a staircase-like structure, which reflects the agent's embodiment.
Decentralized Traffic Flow Optimization Through Intrinsic Motivation
Charles W. Davidson College Of Engineering, San Jose State University, CA, USA（桑杰州立大学查尔斯·W·戴森工程学院）；School of Physics, Engineering and Computer Science, University of Hertfordshire, UK（赫特福德郡大学物理、工程与计算机科学学院）；Computer Science Department, Whitacre Collage of Engineering, Texas Tech University, Texas, USA（德克萨斯理工大学怀特雷学院工程学院计算机科学系）
We describe ACE0, a lightweight platform for evaluating the suitability and viability of AI methods for behaviour discovery in multiagent simulations. Specifically, ACE0 was designed to explore AI methods for multi-agent simulations used in operations research studies related to new technologies such as autonomous aircraft. Simulation environments used in production are often high-fidelity, complex, require significant domain knowledge and as a result have high R&D costs. Minimal and lightweight simulation environments can help researchers and engineers evaluate the viability of new AI technol…
Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory. Children, however, benefit from exposure to language, helping to organize and mediate their thought. We propose LE2 (Language Enhanced Exploration), a learning algorithm leveraging intrinsic motivations and natural language (NL) interactions with a descriptive social partner (SP). Using NL descriptions from the SP, it can learn an NL-conditioned reward function to f…
San Jose State University（圣何塞州立大学）；Emory University（埃默里大学）；University of Hertfordshire（赫特福德大学）；Hebrew University of Jerusalem（耶路撒冷希伯来大学）
Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an information-theoretic approach to intrinsic motivation, based on maximizing an agent's empowerment (the mutual information between its past actions and future states). We show that this approach generalizes previous attempts to formalize intrinsic motivation, and we provide a computationally efficient algorithm for computing the necessary quantities. We test our app…
DeepMind；Google（谷歌）；California Institute of Technology（加州理工学院）
Multi-agent artificial intelligence research promises a path to develop intelligent technologies that are more human-like and more human-compatible than those produced by "solipsistic" approaches, which do not consider interactions between agents. Melting Pot is a research tool developed to facilitate work on multi-agent artificial intelligence, and provides an evaluation protocol that measures generalization to novel social partners in a set of canonical test scenarios. Each scenario pairs a physical environment (a "substrate") with a reference set of co-players (a "background population"), t…
University of Southern California（南加州大学）；Netflix（奈飞）
There have been several attempts to define a plausible motivation for a chit-chat dialogue agent that can lead to engaging conversations. In this work, we explore a new direction where the agent specifically focuses on discovering information about its interlocutor. We formalize this approach by defining a quantitative metric. We propose an algorithm for the agent to maximize it. We validate the idea with human evaluation where our system outperforms various baselines. We demonstrate that the metric indeed correlates with the human judgments of engagingness.
Google Brain（谷歌大脑）；DeepMind（深度思维）；University of Toronto（多伦多大学）；University College London（伦敦大学学院）
To learn directed behaviors in complex environments, intelligent agents need to optimize objective functions. Various objectives are known for designing artificial agents, including task rewards and intrinsic motivation. However, it is unclear how the known objectives relate to each other, which objectives remain yet to be discovered, and which objectives better describe the behavior of humans. We introduce the Action Perception Divergence (APD), an approach for categorizing the space of possible objective functions for embodied agents. We show a spectrum that reaches from narrow to general ob…
