Recent work on designing an appropriate distribution of environments has shown promise for training effective generally capable agents. Its success is partly because of a form of adaptive curriculum learning that generates environment instances (or levels) at the frontier of the agent's capabilities. However, such an environment design framework often struggles to find effective levels in challenging design spaces and requires costly interactions with the environment. In this paper, we aim to introduce diversity in the Unsupervised Environment Design (UED) framework. Specifically, we propose a task-agnostic method to identify observed/hidden states that are representative of a given level. The outcome of this method is then utilized to characterize the diversity between two levels, which as we show can be crucial to effective performance. In addition, to improve sampling efficiency, we incorporate the self-play technique that allows the environment generator to automatically generate environments that are of great benefit to the training agent. Quantitatively, our approach, Diversity-induced Environment Design via Self-Play (DivSP), shows compelling performance over existing methods.
相關內容
This letter addresses the problem of trajectory planning in a marsupial robotic system consisting of an unmanned aerial vehicle (UAV) linked to an unmanned ground vehicle (UGV) through a non-taut tether withcontrollable length. To the best of our knowledge, this is the first method that addresses the trajectory planning of a marsupial UGV-UAV with a non-taut tether. The objective is to determine a synchronized collision-free trajectory for the three marsupial system agents: UAV, UGV, and tether. First, we present a path planning solution based on optimal Rapidly-exploring Random Trees (RRT*) with novel sampling and steering techniques to speed-up the computation. This algorithm is able to obtain collision-free paths for the UAV and the UGV, taking into account the 3D environment and the tether. Then, the paper presents a trajectory planner based on non-linear least squares. The optimizer takes into account aspects not considered in the path planning, like temporal constraints of the motion imposed by limits on the velocities and accelerations of the robots , or raising the tether's clearance. Simulated and field test results demonstrate that the approach generates obstacle-free, smooth, and feasible trajectories for the marsupial system.
Cooperative multi-agent reinforcement learning (CMARL) has shown to be promising for many real-world applications. Previous works mainly focus on improving coordination ability via solving MARL-specific challenges (e.g., non-stationarity, credit assignment, scalability), but ignore the policy perturbation issue when testing in a different environment. This issue hasn't been considered in problem formulation or efficient algorithm design. To address this issue, we firstly model the problem as a limited policy adversary Dec-POMDP (LPA-Dec-POMDP), where some coordinators from a team might accidentally and unpredictably encounter a limited number of malicious action attacks, but the regular coordinators still strive for the intended goal. Then, we propose Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers (ROMANCE), which enables the trained policy to encounter diversified and strong auxiliary adversarial attacks during training, thus achieving high robustness under various policy perturbations. Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity. The goal of quality is to minimize the ego-system coordination effect, and a novel diversity regularizer based on sparse action is applied to diversify the behaviors among attackers. The ego-system is then paired with a population of attackers selected from the maintained attacker set, and alternately trained against the constantly evolving attackers. Extensive experiments on multiple scenarios from SMAC indicate our ROMANCE provides comparable or better robustness and generalization ability than other baselines.
Transactive Memory System (TMS) is a group theory that describes how communication can enable the combination of individual minds into a group. While this theory has been extensively studied in human-human groups, it has not yet been formally applied to socially assistive robot design. We demonstrate how the three-phase TMS group communication process-which involves encoding, storage, and retrieval-can be leveraged to improve decision making in socially assistive robots with multiple stakeholders. By clearly defining how the robot is gaining information, storing and updating its memory, and retrieving information from its memory, we believe that socially assistive robots can make better decisions and provide more transparency behind their actions in the group context. Bringing communication theory to robot design can provide a clear framework to help robots integrate better into human-human group dynamics and thus improve their acceptance and use.
Motion forecasting is a key module in an autonomous driving system. Due to the heterogeneous nature of multi-sourced input, multimodality in agent behavior, and low latency required by onboard deployment, this task is notoriously challenging. To cope with these difficulties, this paper proposes a novel agent-centric model with anchor-informed proposals for efficient multimodal motion prediction. We design a modality-agnostic strategy to concisely encode the complex input in a unified manner. We generate diverse proposals, fused with anchors bearing goal-oriented scene context, to induce multimodal prediction that covers a wide range of future trajectories. Our network architecture is highly uniform and succinct, leading to an efficient model amenable for real-world driving deployment. Experiments reveal that our agent-centric network compares favorably with the state-of-the-art methods in prediction accuracy, while achieving scene-centric level inference latency.
Communication via natural language is a crucial aspect of intelligence, and it requires computational models to learn and reason about world concepts, with varying levels of supervision. While there has been significant progress made on fully-supervised non-interactive tasks, such as question-answering and procedural text understanding, much of the community has turned to various sequential interactive tasks, as in semi-Markov text-based games, which have revealed limitations of existing approaches in terms of coherence, contextual awareness, and their ability to learn effectively from the environment. In this paper, we propose a framework for enabling improved functional grounding of agents in text-based games. Specifically, we consider two forms of domain knowledge that we inject into learning-based agents: memory of previous correct actions and affordances of relevant objects in the environment. Our framework supports three representative model classes: `pure' reinforcement learning (RL) agents, RL agents enhanced with knowledge graphs, and agents equipped with language models. Furthermore, we devise multiple injection strategies for the above domain knowledge types and agent architectures, including injection via knowledge graphs and augmentation of the existing input encoding strategies. We perform all experiments on the ScienceWorld text-based game environment, to illustrate the performance of various model configurations in challenging science-related instruction-following tasks. Our findings provide crucial insights on the development of effective natural language processing systems for interactive contexts.
Reinforcement learning (RL) mimics how humans and animals interact with the environment. The setting is somewhat idealized because, in actual tasks, other agents in the environment have their own goals and behave adaptively to the ego agent. To thrive in those environments, the agent needs to influence other agents so their actions become more helpful and less harmful. Research in computational economics distills two ways to influence others directly: by providing tangible goods (mechanism design) and by providing information (information design). This work investigates information design problems for a group of RL agents. The main challenges are two-fold. One is the information provided will immediately affect the transition of the agent trajectories, which introduces additional non-stationarity. The other is the information can be ignored, so the sender must provide information that the receivers are willing to respect. We formulate the Markov signaling game, and develop the notions of signaling gradient and the extended obedience constraints that address these challenges. Our algorithm is efficient on various mixed-motive tasks and provides further insights into computational economics. Our code is available at //github.com/YueLin301/InformationDesignMARL.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators. However, these algorithms can fail in scenarios where the disturbance from target environments is unknown or is intractable to model in simulators. To tackle this problem, we propose a novel model-free actor-critic algorithm -- namely, state-conservative policy optimization (SCPO) -- to learn robust policies without modeling the disturbance in advance. Specifically, SCPO reduces the disturbance in transition dynamics to that in state space and then approximates it by a simple gradient-based regularizer. The appealing features of SCPO include that it is simple to implement and does not require additional knowledge about the disturbance or specially designed simulators. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.
Effective multi-robot teams require the ability to move to goals in complex environments in order to address real-world applications such as search and rescue. Multi-robot teams should be able to operate in a completely decentralized manner, with individual robot team members being capable of acting without explicit communication between neighbors. In this paper, we propose a novel game theoretic model that enables decentralized and communication-free navigation to a goal position. Robots each play their own distributed game by estimating the behavior of their local teammates in order to identify behaviors that move them in the direction of the goal, while also avoiding obstacles and maintaining team cohesion without collisions. We prove theoretically that generated actions approach a Nash equilibrium, which also corresponds to an optimal strategy identified for each robot. We show through extensive simulations that our approach enables decentralized and communication-free navigation by a multi-robot system to a goal position, and is able to avoid obstacles and collisions, maintain connectivity, and respond robustly to sensor noise.
The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems. The rich sensor data can be continuously monitored for intrusion events through anomaly detection. However, conventional threshold-based anomaly detection methods are inadequate due to the dynamic complexities of these systems, while supervised machine learning methods are unable to exploit the large amounts of data due to the lack of labeled data. On the other hand, current unsupervised machine learning approaches have not fully exploited the spatial-temporal correlation and other dependencies amongst the multiple variables (sensors/actuators) in the system for detecting anomalies. In this work, we propose an unsupervised multivariate anomaly detection method based on Generative Adversarial Networks (GANs). Instead of treating each data stream independently, our proposed MAD-GAN framework considers the entire variable set concurrently to capture the latent interactions amongst the variables. We also fully exploit both the generator and discriminator produced by the GAN, using a novel anomaly score called DR-score to detect anomalies by discrimination and reconstruction. We have tested our proposed MAD-GAN using two recent datasets collected from real-world CPS: the Secure Water Treatment (SWaT) and the Water Distribution (WADI) datasets. Our experimental results showed that the proposed MAD-GAN is effective in reporting anomalies caused by various cyber-intrusions compared in these complex real-world systems.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191