Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption that a reward only depends on the immediate state and action. However, a reward sometimes depends on the history of states and actions, which may result in the decision process in a non-Markovian environment. In such environments, agents receive rewards via temporally-extended behaviors sparsely, and the learned policies may be similar. This leads the agents acquired with similar policies generally overfit to the given task and can not quickly adapt to perturbations of environments. To resolve this problem, this paper tries to learn the diverse policies from the history of state-action pairs under a non-Markovian environment, in which a policy dispersion scheme is designed for seeking diverse policy representation. Specifically, we first adopt a transformer-based method to learn policy embeddings. Then, we stack the policy embeddings to construct a dispersion matrix to induce a set of diverse policies. Finally, we prove that if the dispersion matrix is positive definite, the dispersed embeddings can effectively enlarge the disagreements across policies, yielding a diverse expression for the original policy embedding distribution. Experimental results show that this dispersion scheme can obtain more expressive diverse policies, which then derive more robust performance than recent learning baselines under various learning environments.

Solving a collision-aware multi-agent mission planning (task allocation and path finding) problem is challenging due to the requirement of real-time computational performance, scalability, and capability of handling static/dynamic obstacles and tasks in a cluttered environment. This paper proposes a distributed real-time (on the order of millisecond) algorithm DrMaMP, which partitions the entire unassigned task set into subsets via approximation and decomposes the original problem into several single-agent mission planning problems. This paper presents experiments with dynamic obstacles and tasks and conducts optimality and scalability comparisons with an existing method, where DrMaMP outperforms the existing method in both indices. Finally, this paper analyzes the computational burden of DrMaMP which is consistent with the observations from comparisons, and presents the optimality gap in small-size problems.

Simultaneous Localization and Mapping (SLAM) algorithms are frequently deployed to support a wide range of robotics applications, such as autonomous navigation in unknown environments, and scene mapping in virtual reality. Many of these applications require autonomous agents to perform SLAM in highly dynamic scenes. To this end, this tutorial extends a recently introduced, unifying optimization-based SLAM backend framework to environments with moving objects and features. Using this framework, we consider a rapprochement of recent advances in dynamic SLAM. Moreover, we present dynamic EKF SLAM: a novel, filtering-based dynamic SLAM algorithm generated from our framework, and prove that it is mathematically equivalent to a direct extension of the classical EKF SLAM algorithm to the dynamic environment setting. Empirical results with simulated data indicate that dynamic EKF SLAM can achieve high localization and mobile object pose estimation accuracy, as well as high map precision, with high efficiency.

In human-robot collaboration, the objectives of the human are often unknown to the robot. Moreover, even assuming a known objective, the human behavior is also uncertain. In order to plan a robust robot behavior, a key preliminary question is then: How to derive realistic human behaviors given a known objective? A major issue is that such a human behavior should itself account for the robot behavior, otherwise collaboration cannot happen. In this paper, we rely on Markov decision models, representing the uncertainty over the human objective as a probability distribution over a finite set of objective functions (inducing a distribution over human behaviors). Based on this, we propose two contributions: 1) an approach to automatically generate an uncertain human behavior (a policy) for each given objective function while accounting for possible robot behaviors; and 2) a robot planning algorithm that is robust to the above-mentioned uncertainties and relies on solving a partially observable Markov decision process (POMDP) obtained by reasoning on a distribution over human behaviors. A co-working scenario allows conducting experiments and presenting qualitative and quantitative results to evaluate our approach.

We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computational complexity that is independent of the graph size. The architecture of AgentNet differs fundamentally from the architectures of traditional graph neural networks. In AgentNet, some trained \textit{neural agents} intelligently walk the graph, and then collectively decide on the output. We provide an extensive theoretical analysis of AgentNet: We show that the agents can learn to systematically explore their neighborhood and that AgentNet can distinguish some structures that are even indistinguishable by 2-WL. Moreover, AgentNet is able to separate any two graphs which are sufficiently different in terms of subgraphs. We confirm these theoretical results with synthetic experiments on hard-to-distinguish graphs and real-world graph classification tasks. In both cases, we compare favorably not only to standard GNNs but also to computationally more expensive GNN extensions.

Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL algorithms. Many decision-making problems in practice naturally involve multiple agents and require multi-agent reinforcement learning (MARL) under centralized training decentralized execution paradigm. Nevertheless, existing MARL algorithms often adopt standard experience replay where the transitions are uniformly sampled regardless of their importance. Finding prioritized sampling weights that are optimized for MARL experience replay has yet to be explored. To this end, we propose MAC-PO, which formulates optimal prioritized experience replay for multi-agent problems as a regret minimization over the sampling weights of transitions. Such optimization is relaxed and solved using the Lagrangian multiplier approach to obtain the close-form optimal sampling weights. By minimizing the resulting policy regret, we can narrow the gap between the current policy and a nominal optimal policy, thus acquiring an improved prioritization scheme for multi-agent tasks. Our experimental results on Predator-Prey and StarCraft Multi-Agent Challenge environments demonstrate the effectiveness of our method, having a better ability to replay important transitions and outperforming other state-of-the-art baselines.

Explicit communication among humans is key to coordinating and learning. Social learning, which uses cues from experts, can greatly benefit from the usage of explicit communication to align heterogeneous policies, reduce sample complexity, and solve partially observable tasks. Emergent communication, a type of explicit communication, studies the creation of an artificial language to encode a high task-utility message directly from data. However, in most cases, emergent communication sends insufficiently compressed messages with little or null information, which also may not be understandable to a third-party listener. This paper proposes an unsupervised method based on the information bottleneck to capture both referential complexity and task-specific utility to adequately explore sparse social communication scenarios in multi-agent reinforcement learning (MARL). We show that our model is able to i) develop a natural-language-inspired lexicon of messages that is independently composed of a set of emergent concepts, which span the observations and intents with minimal bits, ii) develop communication to align the action policies of heterogeneous agents with dissimilar feature models, and iii) learn a communication policy from watching an expert's action policy, which we term `social shadowing'.

Dispatching vehicle fleets to serve flights is a key task in airport ground handling (AGH). Due to the notable growth of flights, it is challenging to simultaneously schedule multiple types of operations (services) for a large number of flights, where each type of operation is performed by one specific vehicle fleet. To tackle this issue, we first represent the operation scheduling as a complex vehicle routing problem and formulate it as a mixed integer linear programming (MILP) model. Then given the graph representation of the MILP model, we propose a learning assisted large neighborhood search (LNS) method using data generated based on real scenarios, where we integrate imitation learning and graph convolutional network (GCN) to learn a destroy operator to automatically select variables, and employ an off-the-shelf solver as the repair operator to reoptimize the selected variables. Experimental results based on a real airport show that the proposed method allows for handling up to 200 flights with 10 types of operations simultaneously, and outperforms state-of-the-art methods. Moreover, the learned method performs consistently accompanying different solvers, and generalizes well on larger instances, verifying the versatility and scalability of our method.

This paper investigates the distributed event-triggered control problem for a class of uncertain pure-feedback nonlinear multi-agent systems (MASs) with polluted feedback. Under the setting of event-triggered control, substantial challenges exist in both control design and stability analysis for systems in more general non-affine pure-feedback forms wherein all state variables are not directly and continuously available or even polluted due to sensor failures, and thus far very limited results are available in literature. In this work, a nominal control strategy under regular state feedback is firstly developed by combining neural network (NN) approximating with dynamic filtering technique, and then a NN-based distributed event-triggered control strategy is proposed by resorting to a novel replacement policy, making the non-differentiability issue arising from event-triggering setting completely circumvented. Besides, the sensor ineffectiveness is accommodated automatically without using fault detection and diagnosis unit or controller reconfiguration. It is shown that all the internal signals are semi-globally uniformly ultimately bounded (SGUUB) with the aid of several vital lemmas, while the outputs of all the subsystems reaching a consensus without infinitely fast execution. Finally, the efficiency of the developed algorithm are verified via numerical simulation.

Lee et al. (2020) utilize relative-attribute information in robot skill learning, but their GAN-based formulation is restricted to static visual attributes and is not applicable to temporally-extended concepts. This paper adopts a similar setup to works that learn diverse skills or motion styles from largescale offline behavior datasets or demonstrations (Lee & Popović, 2010; Wang et al., 2017; Zhou & Dragan, 2018; Peng et al., 2018b; Luo et al., 2020; Chebotar et al., 2021; Peng et al., 2021). These works emphasize on modeling a variety of reusable motor skills by learning a low-level controller conditioned on skill latent codes. Since the latent codes are inscrutable to humans, for each new task, the user must specify the desirable agent behavior by constructing an engineered symbolic reward and use it to train a separate high-level policy that controls the low-level controller. Our methods are complemented by existing diverse-skill learning methods because skill priors (i.e., pre-trained low-level controllers) allow us to optimize the behavioral reward more efficiently. More recently, there have been works in diffusion-based text-to-motion animation generation (Tevet et al., 2022; Guo et al., 2022). They are similar to this work in the sense that we both allow humans to control the agent behavior through explicit concepts. However, they do not support fine-grained control over the strength of individual behavioral attributes, and their works are not applicable to physics-based character control.