Related papers: BAMAX: Backtrack Assisted Multi-Agent Exploration …

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…

To achieve general-purpose utility, we argue that robots must evolve from passive executors into active Information Retrieval users. In strictly zero-shot settings where no prior demonstrations exist, robots face a critical information gap,…

Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively…

Autonomous exploration in unknown environments remains a fundamental challenge in robotics, particularly for applications such as search and rescue, industrial inspection, and planetary exploration. Multi-robot active SLAM presents a…

Animals and robots exist in a physical world and must coordinate their bodies to achieve behavioral objectives. With recent developments in deep reinforcement learning, it is now possible for scientists and engineers to obtain sensorimotor…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

In this work, we present a novel cooperative multi-agent reinforcement learning method called \textbf{Loc}ality based \textbf{Fac}torized \textbf{M}ulti-Agent \textbf{A}ctor-\textbf{C}ritic (Loc-FACMAC). Existing state-of-the-art…

We propose a novel complete algorithm for multi-agent pathfinding (MAPF) called lazy constraints addition search for MAPF (LaCAM). MAPF is a problem of finding collision-free paths for multiple agents on graphs and is the foundation of…

Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three…

A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment. It is important for the agent to explore suboptimal actions as well as to pick actions with highest known rewards. Yet, in…

This paper presents a self-contained system for the robust utilization of aerial robots in the autonomous exploration of cave environments to help human explorers, first responders, and speleologists. The proposed system is generally…

We outline our work on evaluating robots that assist older adults by engaging with them through multiple modalities that include physical interaction. Our thesis is that to increase the effectiveness of assistive robots: 1) robots need to…

Swarm robotic search is concerned with searching targets in unknown environments (e.g., for search and rescue or hazard localization), using a large number of collaborating simple mobile robots. In such applications, decentralized swarm…

This paper presents a comprehensive overview of exploration strategies utilized in both 2D and 3D environments, focusing on autonomous multi-robot systems designed for building exploration and fire detection. We explore the limitations of…

We propose a new ensemble framework for supervised learning, called machine collaboration (MaC), using a collection of base machines for prediction tasks. Unlike bagging/stacking (a parallel & independent framework) and boosting (a…

In reinforcement learning, we typically refer to unsupervised pre-training when we aim to pre-train a policy without a priori access to the task specification, i.e. rewards, to be later employed for efficient learning of downstream tasks.…

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy. This contributes to the problem of high sample complexity,…

Real-world applications require a robot operating in the physical world with awareness of potential risks besides accomplishing the task. A large part of risky behaviors arises from interacting with objects in ignorance of affordance. To…

Quadruped robots have the distinct ability to adapt their body and step height to navigate through cluttered environments. Nonetheless, for these robots to utilize their full potential in real-world scenarios, they require awareness of…

Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…