1 code implementation • 15 Mar 2024 • Xinrun Xu, Yuxin Wang, Chaoyi Xu, Ziluo Ding, Jiechuan Jiang, Zhiming Ding, Börje F. Karlsson
The swift evolution of Large-scale Models (LMs), either language-focused or multi-modal, has garnered extensive attention in both academy and industry.
2 code implementations • 5 Mar 2024 • Weihao Tan, Ziluo Ding, Wentao Zhang, Boyu Li, Bohan Zhou, Junpeng Yue, Haochong Xia, Jiechuan Jiang, Longtao Zheng, Xinrun Xu, Yifei Bi, Pengjie Gu, Xinrun Wang, Börje F. Karlsson, Bo An, Zongqing Lu
Despite the success in specific tasks and scenarios, existing foundation agents, empowered by large models (LMs) and advanced tools, still cannot generalize to different scenarios, mainly due to dramatic differences in the observations and actions across scenarios.
no code implementations • 10 Jan 2024 • Jiechuan Jiang, Kefan Su, Zongqing Lu
Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner.
no code implementations • NeurIPS 2023 • Bohan Zhou, Ke Li, Jiechuan Jiang, Zongqing Lu
Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem.
no code implementations • 16 Feb 2023 • Hao Luo, Jiechuan Jiang, Zongqing Lu
To help the policy improvement be stable and monotonic, we propose model-based decentralized policy optimization (MDPO), which incorporates a latent variable function to help construct the transition and reward function from an individual perspective.
no code implementations • 2 Feb 2023 • Jiechuan Jiang, Zongqing Lu
To tackle this challenge, we propose best possible operator, a novel decentralized operator, and prove that the policies of agents will converge to the optimal joint policy if each agent independently updates its individual state-action value by the operator.
no code implementations • 17 Sep 2022 • Kefan Su, Siyuan Zhou, Jiechuan Jiang, Chuang Gan, Xiangjun Wang, Zongqing Lu
Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL).
no code implementations • 29 Sep 2021 • Jiechuan Jiang, Zongqing Lu
OTC is simple yet effective to increase data efficiency and improve agent policies in online tuning.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 4 Aug 2021 • Jiechuan Jiang, Zongqing Lu
In this paper, we propose a framework for offline decentralized multi-agent reinforcement learning, which exploits value deviation and transition normalization to deliberately modify the transition probabilities.
no code implementations • 4 Aug 2021 • Xiaopeng Yu, Jiechuan Jiang, Wanpeng Zhang, Haobin Jiang, Zongqing Lu
When one agent interacts with a multi-agent environment, it is challenging to deal with various opponents unseen before.
no code implementations • 1 Jan 2021 • Jiechuan Jiang, Zongqing Lu
In multi-agent reinforcement learning (MARL), the learning rates of actors and critic are mostly hand-tuned and fixed.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 28 Sep 2020 • Jiechuan Jiang, Zongqing Lu
EOI learns a probabilistic classifier that predicts a probability distribution over agents given their observation and gives each agent an intrinsic reward of being correctly predicted by the classifier.
Multi-agent Reinforcement Learning reinforcement-learning +1
2 code implementations • 10 Jun 2020 • Jiechuan Jiang, Zongqing Lu
EOI learns a probabilistic classifier that predicts a probability distribution over agents given their observation and gives each agent an intrinsic reward of being correctly predicted by the classifier.
2 code implementations • NeurIPS 2019 • Jiechuan Jiang, Zongqing Lu
Fairness is essential for human society, contributing to stability and productivity.
no code implementations • 21 Apr 2019 • Jiechuan Jiang, Zongqing Lu
Sparse reward is one of the biggest challenges in reinforcement learning (RL).
4 code implementations • ICLR 2020 • Jiechuan Jiang, Chen Dun, Tiejun Huang, Zongqing Lu
The key is to understand the mutual interplay between agents.
no code implementations • NeurIPS 2018 • Jiechuan Jiang, Zongqing Lu
Our model leads to efficient and effective communication for large-scale multi-agent cooperation.