SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning

Value-decomposition methods, which reduce the difficulty of a multi-agent system by decomposing the joint state-action space into local observation-action spaces, have become popular in cooperative multi-agent reinforcement learning (MARL). However, value-decomposition methods still have the problems of tremendous sample consumption for training and lack of active exploration. In this paper, we propose a scalable value-decomposition exploration (SVDE) method, which includes a scalable training mechanism, intrinsic reward design, and explorative experience replay. The scalable training mechanism asynchronously decouples strategy learning with environmental interaction, so as to accelerate sample generation in a MapReduce manner. For the problem of lack of exploration, an intrinsic reward design and explorative experience replay are proposed, so as to enhance exploration to produce diverse samples and filter non-novel samples, respectively. Empirically, our method achieves the best performance on almost all maps compared to other popular algorithms in a set of StarCraft II micromanagement games. A data-efficiency experiment also shows the acceleration of SVDE for sample collection and policy convergence, and we demonstrate the effectiveness of factors in SVDE through a set of ablation experiments.

An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three novel techniques in this framework. First, we propose a matrix decomposition-based method to compress the intermediate output of a neural network to reduce the communication volume between the edge device and the cloud server. Second, we eliminate particular links in the model without affecting the convergence performance in fine-tuning. Third, we implement our system atop PyTorch to allow users to easily extend their existing training scripts to enjoy the efficient edge and cloud collaborative learning. Experiments results on 9 NLP datasets show that our framework can reduce the communication traffic by 96 times with little impact on the model accuracy.

Dynamic Contrastive Distillation for Image-Text Retrieval

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable). To alleviate this problem, we present a novel plug-in dynamic contrastive distillation (DCD) framework to compress the large VLP models for the ITR task. Technically, we face the following two challenges: 1) the typical uni-modal metric learning approach is difficult to directly apply to the cross-modal tasks, due to the limited GPU memory to optimize too many negative samples during handling cross-modal fusion features. 2) it is inefficient to static optimize the student network from different hard samples, which have different effects on distillation learning and student network optimization. We try to overcome these challenges from two points. First, to achieve multi-modal contrastive learning, and balance the training costs and effects, we propose to use a teacher network to estimate the difficult samples for students, making the students absorb the powerful knowledge from pre-trained teachers, and master the knowledge from hard samples. Second, to dynamic learn from hard sample pairs, we propose dynamic distillation to dynamically learn samples of different difficulties, from the perspective of better balancing the difficulty of knowledge and students' self-learning ability. We successfully apply our proposed DCD strategy to two state-of-the-art vision-language pretrained models, i.e. ViLT and METER. Extensive experiments on MS-COCO and Flickr30K benchmarks show the effectiveness and efficiency of our DCD framework. Encouragingly, we can speed up the inference at least 129$\times$ compared to the existing ITR models.

Parameter-Efficient and Student-Friendly Knowledge Distillation

Knowledge distillation (KD) has been extensively employed to transfer the knowledge from a large teacher model to the smaller students, where the parameters of the teacher are fixed (or partially) during training. Recent studies show that this mode may cause difficulties in knowledge transfer due to the mismatched model capacities. To alleviate the mismatch problem, teacher-student joint training methods, e.g., online distillation, have been proposed, but it always requires expensive computational cost. In this paper, we present a parameter-efficient and student-friendly knowledge distillation method, namely PESF-KD, to achieve efficient and sufficient knowledge transfer by updating relatively few partial parameters. Technically, we first mathematically formulate the mismatch as the sharpness gap between their predictive distributions, where we show such a gap can be narrowed with the appropriate smoothness of the soft label. Then, we introduce an adapter module for the teacher and only update the adapter to obtain soft labels with appropriate smoothness. Experiments on a variety of benchmarks show that PESF-KD can significantly reduce the training cost while obtaining competitive results compared to advanced online distillation methods. Code will be released upon acceptance.

Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning for incomplete information environments has attracted extensive attention from researchers. However, due to the slow sample collection and poor sample exploration, there are still some problems in multi-agent reinforcement learning, such as unstable model iteration and low training efficiency. Moreover, most of the existing distributed framework are proposed for single-agent reinforcement learning and not suitable for multi-agent. In this paper, we design an distributed MARL framework based on the actor-work-learner architecture. In this framework, multiple asynchronous environment interaction modules can be deployed simultaneously, which greatly improves the sample collection speed and sample diversity. Meanwhile, to make full use of computing resources, we decouple the model iteration from environment interaction, and thus accelerate the policy iteration. Finally, we verified the effectiveness of propose framework in MaCA military simulation environment and the SMAC 3D realtime strategy gaming environment with imcomplete information characteristics.

Where Does the Performance Improvement Come From? - A Reproducibility Concern about Image-Text Retrieval

This paper seeks to provide the information retrieval community with some reflections on the current improvements of retrieval learning through the analysis of the reproducibility aspects of image-text retrieval models. For the latter part of the past decade, image-text retrieval has gradually become a major research direction in the field of information retrieval because of the growth of multi-modal data. Many researchers use benchmark datasets like MS-COCO and Flickr30k to train and assess the performance of image-text retrieval algorithms. Research in the past has mostly focused on performance, with several state-of-the-art methods being proposed in various ways. According to their claims, these approaches achieve better modal interactions and thus better multimodal representations with greater precision. In contrast to those previous works, we focus on the repeatability of the approaches and the overall examination of the elements that lead to improved performance by pretrained and nonpretrained models in retrieving images and text. To be more specific, we first examine the related reproducibility concerns and why the focus is on image-text retrieval tasks, and then we systematically summarize the current paradigm of image-text retrieval models and the stated contributions of those approaches. Second, we analyze various aspects of the reproduction of pretrained and nonpretrained retrieval models. Based on this, we conducted ablation experiments and obtained some influencing factors that affect retrieval recall more than the improvement claimed in the original paper. Finally, we also present some reflections and issues that should be considered by the retrieval community in the future. Our code is freely available at https://github.com/WangFei-2019/Image-text-Retrieval.

NNCFR: Minimize Counterfactual Regret with Neural Networks

Counterfactual Regret Minimization (CFR)} is the popular method for finding approximate Nash equilibrium in two-player zero-sum games with imperfect information. CFR solves games by travsersing the full game tree iteratively, which limits its scalability in larger games. When applying CFR to solve large-scale games in previously, large-scale games are abstracted into small-scale games firstly. Secondly, CFR is used to solve the abstract game. And finally, the solution strategy is mapped back to the original large-scale game. However, this process requires considerable expert knowledge, and the accuracy of abstraction is closely related to expert knowledge. In addition, the abstraction also loses certain information, which will eventually affect the accuracy of the solution strategy. Towards this problem, a recent method, \textit{Deep CFR} alleviates the need for abstraction and expert knowledge by applying deep neural networks directly to CFR in full games. In this paper, we introduces \textit{Neural Network Counterfactual Regret Minimization (NNCFR)}, an improved variant of \textit{Deep CFR} that has a faster convergence by constructing a dueling netwok as the value network. Moreover, an evaluation module is designed by combining the value network and Monte Carlo, which reduces the approximation error of the value network. In addition, a new loss function is designed in the procedure of training policy network in the proposed \textit{NNCFR}, which can be good to make the policy network more stable. The extensive experimental tests are conducted to show that the \textit{NNCFR} converges faster and performs more stable than \textit{Deep CFR}, and outperforms \textit{Deep CFR} with respect to exploitability and head-to-head performance on test games.

RLCFR: Minimize Counterfactual Regret by Deep Reinforcement Learning

Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies that mostly explore for solving larger scale problems or accelerating solution efficiency, we propose a framework, RLCFR, which aims at improving the generalization ability of the CFR method. In the RLCFR, the game strategy is solved by the CFR in a reinforcement learning framework. And the dynamic procedure of iterative interactive strategy updating is modeled as a Markov decision process (MDP). Our method, RLCFR, then learns a policy to select the appropriate way of regret updating in the process of iteration. In addition, a stepwise reward function is formulated to learn the action policy, which is proportional to how well the iteration strategy is at each step. Extensive experimental results on various games have shown that the generalization ability of our method is significantly improved compared with existing state-of-the-art methods.