Over-communicate no more: Situated RL agents learn concise communication protocols

• URL: http://arxiv.org/abs/2211.01480v1
• Date: Wed, 2 Nov 2022 21:08:14 GMT
• Title: Over-communicate no more: Situated RL agents learn concise communication protocols
• Authors: Aleksandra Kalinowska, Elnaz Davoodi, Florian Strub, Kory W Mathewson, Ivana Kajic, Michael Bowling, Todd D Murphey, Patrick M Pilarski
• Abstract summary: It is unclear how to design artificial agents that can learn to effectively and efficiently communicate with each other. Much research on communication emergence uses reinforcement learning (RL) We explore situated communication in a multi-step task, where the acting agent has to forgo an environmental action to communicate. We find that while all tested pressures can disincentivise over-communication, situated communication does it most effectively and, unlike the cost on effort, does not negatively impact emergence.
• Score: 78.28898217947467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While it is known that communication facilitates cooperation in multi-agent settings, it is unclear how to design artificial agents that can learn to effectively and efficiently communicate with each other. Much research on communication emergence uses reinforcement learning (RL) and explores unsituated communication in one-step referential tasks -- the tasks are not temporally interactive and lack time pressures typically present in natural communication. In these settings, agents may successfully learn to communicate, but they do not learn to exchange information concisely -- they tend towards over-communication and an inefficient encoding. Here, we explore situated communication in a multi-step task, where the acting agent has to forgo an environmental action to communicate. Thus, we impose an opportunity cost on communication and mimic the real-world pressure of passing time. We compare communication emergence under this pressure against learning to communicate with a cost on articulation effort, implemented as a per-message penalty (fixed and progressively increasing). We find that while all tested pressures can disincentivise over-communication, situated communication does it most effectively and, unlike the cost on effort, does not negatively impact emergence. Implementing an opportunity cost on communication in a temporally extended environment is a step towards embodiment, and might be a pre-condition for incentivising efficient, human-like communication.

Related papers

• Learning Multi-Agent Communication with Contrastive Learning [3.816854668079928]
  We introduce an alternative perspective where communicative messages are considered as different incomplete views of the environment state. By examining the relationship between messages sent and received, we propose to learn to communicate using contrastive learning. In communication-essential environments, our method outperforms previous work in both performance and learning speed.
  arXiv  Detail & Related papers  (2023-07-03T23:51:05Z)
• CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society [58.04479313658851]
  This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents. We propose a novel communicative agent framework named role-playing. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems.
  arXiv  Detail & Related papers  (2023-03-31T01:09:00Z)
• AC2C: Adaptively Controlled Two-Hop Communication for Multi-Agent Reinforcement Learning [4.884877440051105]
  We propose a novel communication protocol called Adaptively Controlled Two-Hop Communication (AC2C) AC2C employs an adaptive two-hop communication strategy to enable long-range information exchange among agents to boost performance. We evaluate AC2C on three cooperative multi-agent tasks, and the experimental results show that it outperforms relevant baselines with lower communication costs.
  arXiv  Detail & Related papers  (2023-02-24T09:00:34Z)
• Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems [51.6210785955659]
  Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world application where noise and potential attackers exist, the safety of communication-based policies becomes a severe issue that is underexplored. In this work, we consider an environment with $N$ agents, where the attacker may arbitrarily change the communication from any $CfracN-12$ agents to a victim agent.
  arXiv  Detail & Related papers  (2022-06-21T07:32:18Z)
• The Enforcers: Consistent Sparse-Discrete Methods for Constraining Informative Emergent Communication [5.432350993419402]
  Communication enables agents to cooperate to achieve their goals. Recent work in learning sparse communication suffers from high variance training where, the price of decreasing communication is a decrease in reward, particularly in cooperative tasks. This research addresses the above issues by limiting the loss in reward of decreasing communication and eliminating the penalty for discretization.
  arXiv  Detail & Related papers  (2022-01-19T07:31:06Z)
• Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents [83.52684405389445]
  We introduce the collaborative multi-object navigation task CoMON. In this task, an oracle agent has detailed environment information in the form of a map. It communicates with a navigator agent that perceives the environment visually and is tasked to find a sequence of goals. We show that the emergent communication can be grounded to the agent observations and the spatial structure of the 3D environment.
  arXiv  Detail & Related papers  (2021-10-12T06:56:11Z)
• Adversarial Attacks On Multi-Agent Communication [80.4392160849506]
  Modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Such advantages rely heavily on communication channels which have been shown to be vulnerable to security breaches. In this paper, we explore such adversarial attacks in a novel multi-agent setting where agents communicate by sharing learned intermediate representations.
  arXiv  Detail & Related papers  (2021-01-17T00:35:26Z)
• Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations [59.608216900601384]
  We study agents that learn to communicate via actuating their joints in a 3D environment. We show that under realistic assumptions, a non-uniform distribution of intents and a common-knowledge energy cost, these agents can find protocols that generalize to novel partners.
  arXiv  Detail & Related papers  (2020-10-29T19:23:10Z)
• Learning to Communicate Using Counterfactual Reasoning [2.8110705488739676]
  This paper introduces the novel multi-agent counterfactual communication learning (MACC) method. MACC adapts counterfactual reasoning in order to overcome the credit assignment problem for communicating agents. Our experiments show that MACC is able to outperform the state-of-the-art baselines in four different scenarios in the Particle environment.
  arXiv  Detail & Related papers  (2020-06-12T14:02:04Z)
• Learning Individually Inferred Communication for Multi-Agent Cooperation [37.56115000150748]
  We propose Individually Inferred Communication (I2C) to enable agents to learn a prior for agent-agent communication. The prior knowledge is learned via causal inference and realized by a feed-forward neural network. I2C can not only reduce communication overhead but also improve the performance in a variety of multi-agent cooperative scenarios.
  arXiv  Detail & Related papers  (2020-06-11T14:07:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.