Jian Wang

Bingyu Hui, Lebin Yu, Quanming Yao et al.

Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents, requiring them to coordinate well with collaborators from a diverse, potentially evolving, pool of partners that are not seen before without any fine-tuning. Population-based training, which approximates such an evolving partner pool, has been proven to provide good zero-shot coordination performance; nevertheless, existing methods are limited by computational resources, mainly focusing on optimizing diversity in small populations while neglecting the potential performance gains from scaling population size. To address this issue, this paper proposes the Scalable Population Training (ScaPT), an efficient RL training framework comprising two key components: a meta-agent that efficiently realizes a population by selectively sharing parameters across agents, and a mutual information regularizer that guarantees population diversity. To empirically validate the effectiveness of ScaPT, this paper evaluates it along with representational frameworks in Hanabi cooperative game and confirms its superiority.

Jian Wang, Yourui Huangfu, Rong Li et al.

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot topic in both industrial and academic communities. Many frameworks, such as federated learning and federated distillation, have been proposed. However, few of them takes good care of obstacles such as the time-varying topology resulted by the characteristics of wireless networks. In this paper, we propose a distributed learning framework based on a scalable deep neural network (DNN) design. By exploiting the permutation equivalence and invariance properties of the learning tasks, the DNNs with different scales for different clients can be built up based on two basic parameter sub-matrices. Further, model aggregation can also be conducted based on these two sub-matrices to improve the learning convergence and performance. Finally, simulation results verify the benefits of the proposed framework by compared with some baselines.

Jian Wang, Chen Xu, Rong Li et al.

To improve the system performance towards the Shannon limit, advanced radio resource management mechanisms play a fundamental role. In particular, scheduling should receive much attention, because it allocates radio resources among different users in terms of their channel conditions and QoS requirements. The difficulties of scheduling algorithms are the tradeoffs need to be made among multiple objectives, such as throughput, fairness and packet drop rate. We propose a smart scheduling scheme based on deep reinforcement learning (DRL). We not only verify the performance gain achieved, but also provide implementation-friend designs, i.e., a scalable neural network design for the agent and a virtual environment training framework. With the scalable neural network design, the DRL agent can easily handle the cases when the number of active users is time-varying without the need to redesign and retrain the DRL agent. Training the DRL agent in a virtual environment offline first and using it as the initial version in the practical usage helps to prevent the system from suffering from performance and robustness degradation due to the time-consuming training. Through both simulations and field tests, we show that the DRL-based smart scheduling outperforms the conventional scheduling method and can be adopted in practical systems.

Chen Xu, Jian Wang, Tianhang Yu et al.

In this paper, the downlink packet scheduling problem for cellular networks is modeled, which jointly optimizes throughput, fairness and packet drop rate. Two genie-aided heuristic search methods are employed to explore the solution space. A deep reinforcement learning (DRL) framework with A2C algorithm is proposed for the optimization problem. Several methods have been utilized in the framework to improve the sampling and training efficiency and to adapt the algorithm to a specific scheduling problem. Numerical results show that DRL outperforms the baseline algorithm and achieves similar performance as genie-aided methods without using the future information.

Yourui Huangfu, Jian Wang, Chen Xu et al.

In this paper, we propose a neural-network-based realistic channel model with both the similar accuracy as deterministic channel models and uniformity as stochastic channel models. To facilitate this realistic channel modeling, a multi-domain channel embedding method combined with self-attention mechanism is proposed to extract channel features from multiple domains simultaneously. This 'one model to fit them all' solution employs available wireless channel data as the only data set for self-supervised pre-training. With the permission of users, network operators or other organizations can make use of some available user specific data to fine-tune this pre-trained realistic channel model for applications on channel-related downstream tasks. Moreover, even without fine-tuning, we show that the pre-trained realistic channel model itself is a great tool with its understanding of wireless channel.

Jian Wang, Chen Xu, Yourui Huangfu et al.

Integrating artificial intelligence (AI) into wireless networks has drawn significant interest in both industry and academia. A common solution is to replace partial or even all modules in the conventional systems, which is often lack of efficiency and robustness due to their ignoring of expert knowledge. In this paper, we take deep reinforcement learning (DRL) based scheduling as an example to investigate how expert knowledge can help with AI module in cellular networks. A simulation platform, which has considered link adaption, feedback and other practical mechanisms, is developed to facilitate the investigation. Besides the traditional way, which is learning directly from the environment, for training DRL agent, we propose two novel methods, i.e., learning from a dual AI module and learning from the expert solution. The results show that, for the considering scheduling problem, DRL training procedure can be improved on both performance and convergence speed by involving the expert knowledge. Hence, instead of replacing conventional scheduling module in the system, adding a newly introduced AI module, which is capable to interact with the conventional module and provide more flexibility, is a more feasible solution.