Focusing on multi-agent path finding as an exemplary problem, this paper proposes to simplify two popular approaches to MAPF, namely multi-agent reinforcement learning and adaptive search, to enable seamless combination and transferability of methods without substantial engineering effort.
M3W is a novel approach that applies mixture-of-experts (MoE) to world model instead of policy, enabling both learning and planning, and demonstrates superior performance, sample efficiency, and multi-task adaptability.
Zi-Jie Zhao, Zhong Zhao, Kaixuan Xu et al.· Neural Information Processin...· 9 citations
This work introduces a novel MARL framework, Multi-Agent Divergence Policy Optimization (MADPO) with Mutual Policy Divergence Maximization (Mutual PDM), and proposes a new extension of CCS divergence for measuring policy divergence of more than two agents, the Generalized Conditional Cauchy-Schwarz (GCCS) divergence.
Haowen Dou, Lujuan Dang, Mingfei Lu et al.· IEEE Transactions on Pattern...· 0 citations
Despite recent advances in multi-agent path finding, achieving robust coordination in dynamic and crowded warehouse environments remains a bottleneck due to training instability and inefficient credit assignment. To address these challenges, we propose BeMapper, a novel evolutionary-augmented reinforcement learning framework that integrates a multi-agent bidirectionally-coordinated network (BicNet) with a distributed actor-critic architecture. Technically, our core novelty lies in three aspects: (1) A bidirectional feature fusion mechanism that enables agents to perceive collective spatial states beyond local observations; (2) An evolutionary-driven critic selection strategy that iteratively propagates high-performing models to accelerate convergence; (3) A multi-metric scoring system that incorporates success rate variance to penalize unstable behaviors and resolve credit assignment ambiguity. Extensive experiments demonstrate the superiority of BeMapper: it achieves a 98.66% mean success rate, outperforming state-of-the-art baselines Mapper (95.51%) and BicNet (93.78%) by 3.15%and 4.88%, respectively. Crucially, BeMapper yields a significantly higher average reward of 18.81, representing a relative improvement of 1.65 over Mapper and a substantial leap over BicNet's near-zero performance (0.04). Furthermore, in more crowded scenarios, BeMapper reduces the average travel steps to 36, being 5-9 steps shorter than competing methods, effectively enhancing operational throughput while ensuring robustness for large-scale industrial automation.
One of the main challenges in the field of artificial intelligence, and reinforcement learning (RL) in particular, is the development of generalist and flexible agents capable of solving multiple tasks—each requiring the agent to learn a potentially new, specialized behavior. Tackling this challenge requires agents to learn behaviors that may involve optimizing a single objective, or trading off between multiple conflicting objectives. In this thesis, we study how to design flexible RL agents that can, in a sample-efficient manner, adapt their behavior to solve any given tasks—each of which is defined by multiple (possibly conflicting) objectives. We introduce new multi-policy methods that empower RL agents to (i) carefully learn multiple behaviors, each specialized in a particular task; and (ii) combine previously-learned behaviors to efficiently identify solutions to novel tasks, which, importantly, may require the agent to assign different preferences to each of its new objectives. The methods we introduce have strong theoretical guarantees regarding the optimality of the set of behaviors learned by agents and their capability to solve new tasks in a zero-shot manner, even in the presence of function approximation errors. We evaluate the proposed methods in various challenging multi-task and multi-objective RL problems and show that our algorithms outperform various current state-of-the-art methods in domains with both discrete and continuous state and action spaces.
L. N. Alegre, Ana L. C. Bazzan, Bruno C. da Silva· Anais do XXXIX Concurso de T...· 0 citations
Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .
Joe Eappen, Zikang Xiong, S. Iyengar et al.· IEEE Robotics and Automation...· 0 citations
This work presents OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution and sustains performance improvement over extended optimization horizons.
Yuxin Cheng, Chang Liu, Hanxin Yu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
