Attention-guided contrastive role representations for multi-agent reinforcement learning

Z Hu, Z Zhang, H Li, C Chen, H Ding… - arxiv preprint arxiv …, 2023 - arxiv.org
Real-world multi-agent tasks usually involve dynamic team composition with the emergence
of roles, which should also be a key to efficient cooperation in multi-agent reinforcement …

Confidence-Based Curriculum Learning for Multi-Agent Path Finding

T Phan, J Driscoll, J Romberg, S Koenig - arxiv preprint arxiv:2401.05860, 2024 - arxiv.org
A wide range of real-world applications can be formulated as Multi-Agent Path Finding
(MAPF) problem, where the goal is to find collision-free paths for multiple agents with …

Towards Fault Tolerance in Multi-Agent Reinforcement Learning

Y Shi, H Pei, L Feng, Y Zhang, D Yao - arxiv preprint arxiv:2412.00534, 2024 - arxiv.org
Agent faults pose a significant threat to the performance of multi-agent reinforcement
learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to …

Farthest Agent Selection With Episode-Wise Observations for Real-Time Multi-Agent Reinforcement Learning Applications

H Lee, GS Kim, M Choi, H Baek, S Park - IEEE Access, 2024 - ieeexplore.ieee.org
Multi-agent reinforcement learning (MARL) algorithms have been widely used for many
applications requiring sequential decision-making to maximize the expected rewards …

[PDF][PDF] Attention-Based Recurrency for Multi-Agent Reinforcement Learning under State Uncertainty.

T Phan, F Ritz, J Nüßlein, M Kölle, T Gabor… - AAMAS, 2023 - researchgate.net
State uncertainty poses a major challenge for decentralized coordination, where multiple
agents act according to noisy observations without any access to other agents' information …

Confidence-Based Curricula for Multi-Agent Path Finding via Reinforcement Learning

T Phan, J Driscoll, J Romberg, S Koenig - 2024 - researchsquare.com
A wide range of real-world applications can be formulated as Multi-Agent Path Finding
(MAPF) problem, where the goal is to find collision-free paths for multiple agents with …

Priority Over Quantity: A Self-Incentive Credit Assignment Scheme for Cooperative Multiagent Reinforcement Learning

H Tang, C Wang, S Chang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Centralized training and decentralized execution (CTDE) paradigm is widely employed to
address the nonstationary and partial observability in multiagent reinforcement learning …

[HTML][HTML] A Multi-Agent Centralized Strategy Gradient Reinforcement Learning Algorithm Based on State Transition

L Sheng, H Chen, X Chen - Algorithms, 2024 - mdpi.com
The prevalent utilization of deterministic strategy algorithms in Multi-Agent Deep
Reinforcement Learning (MADRL) for collaborative tasks has posed a significant challenge …

Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments

A Zhaikhan, AH Sayed - arxiv preprint arxiv:2407.04974, 2024 - arxiv.org
This study proposes the use of a social learning method to estimate a global state within a
multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a …

Swarm Behavior Cloning

J Nüßlein, M Zorn, P Altmann… - arxiv preprint arxiv …, 2024 - arxiv.org
In sequential decision-making environments, the primary approaches for training agents are
Reinforcement Learning (RL) and Imitation Learning (IL). Unlike RL, which relies on …