Recent advancements in robotics have enabled robots to navigate complex
scenes or manipulate diverse objects independently. However, robots are still
impotent in many household tasks requiring coordinated behaviors such as
opening doors. The factorization of navigation and manipulation, while
effective for some tasks, fails in scenarios requiring coordinated actions. To
address this challenge, we introduce, HarmonicMM, an end-to-end learning method
that optimizes both navigation and manipulation, showing notable improvement
over existing techniques in everyday tasks. This approach is validated in
simulated and real-world environments and adapts to novel unseen settings
without additional tuning. Our contributions include a new benchmark for mobile
manipulation and the successful deployment in a real unseen apartment,
demonstrating the potential for practical indoor robot deployment in daily
life. More results are on our project site:
this https URL

通过互补性的导航和操作，将机器人的环境感知与行为规划相结合，实现了在日常任务中的协调性行为，从而改善了现有技术。验证了该方法在模拟和真实环境中的有效性，并能够适应新颖的未知环境，无需额外调优。

谐波移动操作

Harmonic Mobile Manipulation

In this paper, we propose a new mutual information framework for multi-agent
reinforcement learning to enable multiple agents to learn coordinated behaviors
by regularizing the accumulated return with the simultaneous mutual information
between multi-agent actions. By introducing a latent variable to induce nonzero
mutual information between multi-agent actions and applying a variational
bound, we derive a tractable lower bound on the considered MMI-regularized
objective function. The derived tractable objective can be interpreted as
maximum entropy reinforcement learning combined with uncertainty reduction of
other agents actions. Applying policy iteration to maximize the derived lower
bound, we propose a practical algorithm named variational maximum mutual
information multi-agent actor-critic, which follows centralized learning with
decentralized execution. We evaluated VM3-AC for several games requiring
coordination, and numerical results show that VM3-AC outperforms other MARL
algorithms in multi-agent tasks requiring high-quality coordination.

本文提出了一种新的用于多智能体强化学习的互信息框架，以实现多个智能体协调行为，并通过同时多智能体行为间的互信息来规范累积收益。将多个智能体行为间的互信息引入一个潜在变量，应用变分下界，得到了一个可处理的目标函数下界，该下界可以解释为最大熵强化学习与其他智能体行为的不确定性降低相结合，通过将此下界最大化，提出了一个名为变分最大互信息的多智能体演员 - 批评家算法 (VM3-AC)，其遵循集中式学习与分散式执行。在多个需要协调的游戏中对 VM3-AC 进行了评估，数值结果表明 VM3-AC 在需要高质量协调的多智能体任务上胜过其他多智能体强化学习算法。

多智能体强化学习中基于互信息协调的变分方法

A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning

Coordinated online behaviors are an essential part of information and
influence operations, as they allow a more effective disinformation's spread.
Most studies on coordinated behaviors involved manual investigations, and the
few existing computational approaches make bold assumptions or oversimplify the
problem to make it tractable. Here, we propose a new network-based framework
for uncovering and studying coordinated behaviors on social media. Our research
extends existing systems and goes beyond limiting binary classifications of
coordinated and uncoordinated behaviors. It allows to expose different
coordination patterns and to estimate the degree of coordination that
characterizes diverse communities. We apply our framework to a dataset
collected during the 2019 UK General Election, detecting and characterizing
coordinated communities that participated in the electoral debate. Our work
conveys both theoretical and practical implications and provides more nuanced
and fine-grained results for studying online information manipulation.

我们提出了一种基于网络的框架，用于揭示和研究社交媒体上协调行为，扩展现有系统并允许暴露不同的协调模式以及估计表征不同社区的协调程度。我们将我们的框架应用于收集在 2019 年英国大选期间的数据集，检测并表征了参与选举辩论的协调社区。我们的工作提供了研究在线信息操纵的更加细粒度和微妙的结果，具有重要的理论和实践意义。