Search Results for author: Wenshuai Zhao

Found 9 papers, 4 papers with code

AgentMixer: Multi-Agent Correlated Policy Factorization

no code implementations16 Jan 2024 Zhiyuan Li, Wenshuai Zhao, Lijun Wu, Joni Pajarinen

Inspired by the concept of correlated equilibrium, we propose to introduce a \textit{strategy modification} to provide a mechanism for agents to correlate their policies.

Imitation Learning Multi-agent Reinforcement Learning

Optimistic Multi-Agent Policy Gradient for Cooperative Tasks

1 code implementation3 Nov 2023 Wenshuai Zhao, Yi Zhao, Zhiyuan Li, Juho Kannala, Joni Pajarinen

However, with function approximation optimism can amplify overestimation and thus fail on complex tasks.

Q-Learning

Simplified Temporal Consistency Reinforcement Learning

1 code implementation15 Jun 2023 Yi Zhao, Wenshuai Zhao, Rinu Boney, Juho Kannala, Joni Pajarinen

This applies when using pure planning with a dynamics model conditioned on the representation, but, also when utilizing the representation as policy and value function features in model-free RL.

Decision Making reinforcement-learning +2

Learning Progress Driven Multi-Agent Curriculum

no code implementations20 May 2022 Wenshuai Zhao, Zhiyuan Li, Joni Pajarinen

Inspired by the success of CRL in single-agent settings, a few works have attempted to apply CRL to multi-agent reinforcement learning (MARL) using the number of agents to control task difficulty.

Multi-agent Reinforcement Learning Open-Ended Question Answering +3

Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning

1 code implementation18 Aug 2020 Wenshuai Zhao, Jorge Peña Queralta, Li Qingqing, Tomi Westerlund

In this work, we are particularly interested in analyzing how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems where the operation of the different robots is not necessarily homogeneous.

Multi-agent Reinforcement Learning reinforcement-learning +1

Ubiquitous Distributed Deep Reinforcement Learning at the Edge: Analyzing Byzantine Agents in Discrete Action Spaces

no code implementations18 Aug 2020 Wenshuai Zhao, Jorge Peña Queralta, Li Qingqing, Tomi Westerlund

The integration of edge computing in next-generation mobile networks is bringing low-latency and high-bandwidth ubiquitous connectivity to a myriad of cyber-physical systems.

Edge-computing

Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation

1 code implementation17 Apr 2020 Wenshuai Zhao, Dihong Jiang, Jorge Peña Queralta, Tomi Westerlund

We present a multi-scale supervised 3D U-Net, MSS U-Net, to automatically segment kidneys and kidney tumors from CT images.

Computed Tomography (CT) Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.