no code implementations • 9 Apr 2024 • Jinyuan Feng, Min Chen, Zhiqiang Pu, Tenghai Qiu, Jianqiang Yi
Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently.
no code implementations • 26 Mar 2024 • Qingxu Fu, Zhiqiang Pu, Min Chen, Tenghai Qiu, Jianqiang Yi
Furthermore, we design a prioritized policy gradient approach to compensate for the gap caused by differences in the number of different types of agents.
no code implementations • 26 Mar 2024 • Qingxu Fu, Tenghai Qiu, Jianqiang Yi, Zhiqiang Pu, Xiaolin Ai
This paper proposes a novel hierarchical MARL model called Hierarchical Cooperation Graph Learning (HCGL) for solving general multi-agent problems.
1 code implementation • 20 Jan 2024 • Tianyi Hu, Zhiqiang Pu, Xiaolin Ai, Tenghai Qiu, Jianqiang Yi
Furthermore, we extend MAPD to a customizable version, which can quantify differences among agent policies on specified aspects.
1 code implementation • 13 Nov 2022 • Qingxu Fu, Xiaolin Ai, Jianqiang Yi, Tenghai Qiu, Wanmai Yuan, Zhiqiang Pu
However, they also come with challenges compared with homogeneous systems for multiagent reinforcement learning, such as the non-stationary problem and the policy version iteration issue.
no code implementations • 16 Aug 2022 • Qingxu Fu, Tenghai Qiu, Jianqiang Yi, Zhiqiang Pu, Xiaolin Ai, Wanmai Yuan
SOTA multiagent reinforcement algorithms distinguish themselves in many ways from their single-agent equivalences.
1 code implementation • 5 Aug 2022 • Qingxu Fu, Tenghai Qiu, Zhiqiang Pu, Jianqiang Yi, Wanmai Yuan
Next, based on this novel graph structure, we propose a Cooperation Graph Multiagent Reinforcement Learning (CG-MARL) algorithm, which can efficiently deal with the sparse reward problem in multiagent tasks.
no code implementations • 12 Mar 2022 • Qingxu Fu, Tenghai Qiu, Jianqiang Yi, Zhiqiang Pu, Shiguang Wu
Second, distinct from the well-known attention mechanism, ConcNet has a unique motivational subnetwork to explicitly consider the motivational indices when scoring the observed entities.