In situations where explicit communication is limited, human collaborators act by learning to: (i) infer meaning behind their partner's actions, and (ii) convey private information about the state to their partner implicitly through actions. The first component of this learning process has been well-studied in multi-agent systems, whereas the second --- which is equally crucial for successful collaboration --- has not. To mimic both components mentioned above, thereby completing the learning process, we introduce a novel algorithm: Policy Belief Learning (PBL). PBL uses a belief module to model the other agent's private information and a policy module to form a distribution over actions informed by the belief module. Furthermore, to encourage communication by actions, we propose a novel auxiliary reward which incentivizes one agent to help its partner to make correct inferences about its private information. The auxiliary reward for communication is integrated into the learning of the policy module. We evaluate our approach on a set of environments including a matrix game, particle environment and the non-competitive bidding problem from contract bridge. We show empirically that this auxiliary reward is effective and easy to generalize. These results demonstrate that our PBL algorithm can produce strong pairs of agents in collaborative games where explicit communication is disabled.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual observations with other agents under communication resource constraints. The actor-encoder encodes the raw images and chooses an action based on local observations and messages sent by the other agents. The machine learning agent generates not only an actuator command to the physical device, but also a communication message to the other agents. We formulate a reinf…
Mila-Quebec AI institute（米拉-魁北克人工智能研究所）；Birla Institute of Technology and Science（贝拉理工学院）；MIT（麻省理工学院）；Google（谷歌）；DeepMind（深度思维）
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from …
Peking University（北京大学）；Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）
Being able to predict the mental states of others is a key factor to effective social interaction. It is also crucial for distributed multi-agent systems, where agents are required to communicate and cooperate. In this paper, we introduce such an important social-cognitive skill, i.e. Theory of Mind (ToM), to build socially intelligent agents who are able to communicate and cooperate effectively to accomplish challenging tasks. With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation. Based on the inferred states, the agents d…
Khoury College of Computer Sciences（库利计算机科学学院）；Northeastern University（东北大学）
Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably. Ideally, agents should learn and execute asynchronously instead. Such asynchronous methods also allow temporally extended actions that can take different amounts of time based on the situation and action executed. Unfortunately, current policy gradient methods are not applicable in asynchronous settings, as they assume that agents synchronously reason about action selection at every time step. To allow asy…
Deep Q-Network (DQN) based multi-agent systems (MAS) for reinforcement learning (RL) use various schemes where in the agents have to learn and communicate. The learning is however specific to each agent and communication may be satisfactorily designed for the agents. As more complex Deep QNetworks come to the fore, the overall complexity of the multi-agent system increases leading to issues like difficulty in training, need for higher resources and more training time, difficulty in fine-tuning, etc. To address these issues we propose a simple but efficient DQN based MAS for RL which uses share…
When teams of robots collaborate to complete a task, communication is often necessary. Like humans, robot teammates should implicitly communicate through their actions: but interpreting our partner's actions is typically difficult, since a given action may have many different underlying reasons. Here we propose an alternate approach: instead of not being able to infer whether an action is due to exploration, exploitation, or communication, we define separate roles for each agent. Because each role defines a distinct reason for acting (e.g., only exploit, only communicate), teammates now correc…
Colorado School of Mines（科罗拉多矿业学院）；George Mason University（乔治梅森大学）；University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）
Autonomous robots must communicate about their decisions to gain trust and acceptance. When doing so, robots must determine which actions are causal, i.e., which directly give rise to the desired outcome, so that these actions can be included in explanations. In behavior learning in psychology, this sort of reasoning during an action sequence has been studied extensively in the context of imitation learning. And yet, these techniques and empirical insights are rarely applied to human-robot interaction (HRI). In this work, we discuss the relevance of behavior learning insights for robot intent …
The level of autonomy is increasing in systems spanning multiple domains, but these systems still experience failures. One way to mitigate the risk of failures is to integrate human oversight of the autonomous systems and rely on the human to take control when the autonomy fails. In this work, we formulate a method of collaborative decision making through action suggestions that improves action selection without taking control of the system. Our approach uses each suggestion efficiently by incorporating the implicit information shared through suggestions to modify the agent's belief and achiev…
We propose a novel framework to learn how to communicate with intent, i.e., to transmit messages over a wireless communication channel based on the end-goal of the communication. This stays in stark contrast to classical communication systems where the objective is to reproduce at the receiver side either exactly or approximately the message sent by the transmitter, regardless of the end-goal. Our procedure is general enough that can be adapted to any type of goal or task, so long as the said task is a (almost-everywhere) differentiable function over which gradients can be propagated. We focus…
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 w…
Department of Electrical and Computer Engineering (ECE), Seoul National University（电子与计算机工程系，首尔国立大学）；Interdisciplinary Program in Artificial Intelligence (IPAI), Seoul National University（人工智能交叉项目，首尔国立大学）；ASRI / INMC, Seoul National University（ASRI/INMC，首尔国立大学）
Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（脸书人工智能研究院）
We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019) -- a large-scale crowd-sourced fantasy text-game -- with a dataset of quests. These contain natural language motivations paired with in-game goals and human demonstrations; completing a quest might require dialogue or actions (or both). We introduce a reinforcement learning system that (1) incorporates large-scale language modeling-based and commonsense reasoning-based pre-training to imbue the agent with relevant priors; and (2) leverages a fac…
Collaborative robotics requires effective communication between a robot and a human partner. This work proposes a set of interpretive principles for how a robotic arm can use pointing actions to communicate task information to people by extending existing models from the related literature. These principles are evaluated through studies where English-speaking human subjects view animations of simulated robots instructing pick-and-place tasks. The evaluation distinguishes two classes of pointing actions that arise in pick-and-place tasks: referential pointing (identifying objects) and locating …
Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are limited by the scope of the chosen parametric probability distribution. We show that alternatively to the likelihood based policy gradient, a related objective can be optimized through advantage weighted quantile regression. Our approach models the policy implicitly in the network, which gives the agent the freedom to approximate any distribution in each acti…
University of Oxford（牛津大学）；DeepMind（深度思考）；Facebook AI Research（Facebook人工智能研究院）
When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowing them to act informatively and thereby communicate efficiently with others. Although learning algorithms have recently achieved superhuman performance in a number of two-player, zero-sum games, scalable multi-agent reinforcement learning algorithms that can discover effective strategies and conventions in complex, partially observable settings have proven elusive. We present …
We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work [2], by considering multiple agents communicating over a noisy channel in order to achieve better coordination and cooperation in a multi-agent reinforcement learning (MARL) framework. Specifically, we consider a multi-agent partially observable Markov decision process (MA-POMDP), in which the agents, in addition to interacting with the environment can also communicate with each other over a noisy communication channel. The noisy communication channel is consid…
