Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and hindering their applicability in more challenging scenarios. In contrast, model-based reinforcement learning (MBRL), particularly algorithms integrating planning, such as MuZero, has demonstrated superhuman performance with limited data in many tasks. Hence, we aim to boost the sample efficiency of MARL by adopting model-based approaches. However, incorporating planning and search methods into multi-agent systems poses significant challenges. The expansive action space of multi-agent systems often necessitates leveraging the nearly-independent property of agents to accelerate learning. To tackle this issue, we propose the MAZero algorithm, which combines a centralized model with Monte Carlo Tree Search (MCTS) for policy search. We design a novel network structure to facilitate distributed execution and parameter sharing. To enhance search efficiency in deterministic environments with sizable action spaces, we introduce two novel techniques: Optimistic Search Lambda (OS($\lambda$)) and Advantage-Weighted Policy Optimization (AWPO). Extensive experiments on the SMAC benchmark demonstrate that MAZero outperforms model-free approaches in terms of sample efficiency and provides comparable or better performance than existing model-based methods in terms of both sample and computational efficiency. Our code is available at https://github.com/liuqh16/MAZero.

A flexible active safety motion (FASM) control approach is proposed for the avoidance of dynamic obstacles and the reference tracking in robot manipulators. The distinctive feature of the proposed method lies in its utilization of control barrier functions (CBF) to design flexible CBF-guided safety criteria (CBFSC) with dynamically optimized decay rates, thereby offering flexibility and active safety for robot manipulators in dynamic environments. First, discrete-time CBFs are employed to formulate the novel flexible CBFSC with dynamic decay rates for robot manipulators. Following that, the model predictive control (MPC) philosophy is applied, integrating flexible CBFSC as safety constraints into the receding-horizon optimization problem. Significantly, the decay rates of the designed CBFSC are incorporated as decision variables in the optimization problem, facilitating the dynamic enhancement of flexibility during the obstacle avoidance process. In particular, a novel cost function that integrates a penalty term is designed to dynamically adjust the safety margins of the CBFSC. Finally, experiments are conducted in various scenarios using a Universal Robots 5 (UR5) manipulator to validate the effectiveness of the proposed approach.

One way to personalize chatbot interactions is by establishing common ground with the intended reader. A domain where establishing mutual understanding could be particularly impactful is vaccine concerns and misinformation. Vaccine interventions are forms of messaging which aim to answer concerns expressed about vaccination. Tailoring responses in this domain is difficult, since opinions often have seemingly little ideological overlap. We define the task of tailoring vaccine interventions to a Common-Ground Opinion (CGO). Tailoring responses to a CGO involves meaningfully improving the answer by relating it to an opinion or belief the reader holds. In this paper we introduce TAILOR-CGO, a dataset for evaluating how well responses are tailored to provided CGOs. We benchmark several major LLMs on this task; finding GPT-4-Turbo performs significantly better than others. We also build automatic evaluation metrics, including an efficient and accurate BERT model that outperforms finetuned LLMs, investigate how to successfully tailor vaccine messaging to CGOs, and provide actionable recommendations from this investigation. Code and model weights: https://github.com/rickardstureborg/tailor-cgo Dataset: https://huggingface.co/datasets/DukeNLP/tailor-cgo

In this study, we propose a safety-critical compliant control strategy designed to strictly enforce interaction force constraints during the physical interaction of robots with unknown environments. The interaction force constraint is interpreted as a new force-constrained control barrier function (FC-CBF) by exploiting the generalized contact model and the prior information of the environment, i.e., the prior stiffness and rest position, for robot kinematics. The difference between the real environment and the generalized contact model is approximated by constructing a tracking differentiator, and its estimation error is quantified based on Lyapunov theory. By interpreting strict interaction safety specification as a dynamic constraint, restricting the desired joint angular rates in kinematics, the proposed approach modifies nominal compliant controllers using quadratic programming, ensuring adherence to interaction force constraints in unknown environments. The strict force constraint and the stability of the closed-loop system are rigorously analyzed. Experimental tests using a UR3e industrial robot with different environments verify the effectiveness of the proposed method in achieving the force constraints in unknown environments.

AlphaFold2 has been hailed as a breakthrough in protein folding. It can rapidly predict protein structures with lab-grade accuracy. However, its implementation does not include the necessary training code. OpenFold is the first trainable public reimplementation of AlphaFold. AlphaFold training procedure is prohibitively time-consuming, and gets diminishing benefits from scaling to more compute resources. In this work, we conducted a comprehensive analysis on the AlphaFold training procedure based on Openfold, identified that inefficient communications and overhead-dominated computations were the key factors that prevented the AlphaFold training from effective scaling. We introduced ScaleFold, a systematic training method that incorporated optimizations specifically for these factors. ScaleFold successfully scaled the AlphaFold training to 2080 NVIDIA H100 GPUs with high resource utilization. In the MLPerf HPC v3.0 benchmark, ScaleFold finished the OpenFold benchmark in 7.51 minutes, shown over $6\times$ speedup than the baseline. For training the AlphaFold model from scratch, ScaleFold completed the pretraining in 10 hours, a significant improvement over the seven days required by the original AlphaFold pretraining baseline.

We introduce Efficient Title Reranker via Broadcasting Query Encoder, a novel title reranking technique to achieve efficient title reranking 20x-40x faster than vanilla passage reranker. However, one of the challenges with the training of Efficient Title Reranker is the instability. Analyzing the issue, we found some very difficult ground truths might act as noisy labels causing accuracy to drop as well as some extreme values in model probability output causing nan. To address these issues, we introduce the Sigmoid Trick, a novel technique that reduces the gradient update of both cases resulting in better retrieval efficacy. Experiments showed the effectiveness of ETR and sigmoid trick as we achieved four state-of-the-art positions on the kilt knowledge benchmark.

Among the great successes of Reinforcement Learning (RL), self-play algorithms play an essential role in solving competitive games. Current self-play algorithms optimize the agent to maximize expected win-rates against its current or historical copies, making it often stuck in the local optimum and its strategy style simple and homogeneous. A possible solution is to improve the diversity of policies, which helps the agent break the stalemate and enhances its robustness when facing different opponents. However, enhancing diversity in the self-play algorithms is not trivial. In this paper, we aim to introduce diversity from the perspective that agents could have diverse risk preferences in the face of uncertainty. Specifically, we design a novel reinforcement learning algorithm called Risk-sensitive Proximal Policy Optimization (RPPO), which smoothly interpolates between worst-case and best-case policy learning and allows for policy learning with desired risk preferences. Seamlessly integrating RPPO with population-based self-play, agents in the population optimize dynamic risk-sensitive objectives with experiences from playing against diverse opponents. Empirical results show that our method achieves comparable or superior performance in competitive games and that diverse modes of behaviors emerge. Our code is public online at \url{https://github.com/Jackory/RPBT}.

Within the multimodal field, the key to integrating vision and language lies in establishing a good alignment strategy. Recently, benefiting from the success of self-supervised learning, significant progress has been made in multimodal semantic representation based on pre-trained models for vision and language. However, there is still room for improvement in visual semantic representation. The lack of spatial semantic coherence and vulnerability to noise makes it challenging for current pixel or patch-based methods to accurately extract complex scene boundaries. To this end, this paper develops superpixel as a comprehensive compact representation of learnable image data, which effectively reduces the number of visual primitives for subsequent processing by clustering perceptually similar pixels. To mine more precise topological relations, we propose a Multiscale Difference Graph Convolutional Network (MDGCN). It parses the entire image as a fine-to-coarse hierarchical structure of constituent visual patterns, and captures multiscale features by progressively merging adjacent superpixels as graph nodes. Moreover, we predict the differences between adjacent nodes through the graph structure, facilitating key information aggregation of graph nodes to reason actual semantic relations. Afterward, we design a multi-level fusion rule in a bottom-up manner to avoid understanding deviation by learning complementary spatial information at different regional scales. Our proposed method can be well applied to multiple downstream task learning. Extensive experiments demonstrate that our method is competitive with other state-of-the-art methods in visual reasoning. Our code will be released upon publication.

3D object-level mapping is a fundamental problem in robotics, which is especially challenging when object CAD models are unavailable during inference. In this work, we propose a framework that can reconstruct high-quality object-level maps for unknown objects. Our approach takes multiple RGB-D images as input and outputs dense 3D shapes and 9-DoF poses (including 3 scale parameters) for detected objects. The core idea of our approach is to leverage a learnt generative model for shape categories as a prior and to formulate a probabilistic, uncertainty-aware optimization framework for 3D reconstruction. We derive a probabilistic formulation that propagates shape and pose uncertainty through two novel loss functions. Unlike current state-of-the-art approaches, we explicitly model the uncertainty of the object shapes and poses during our optimization, resulting in a high-quality object-level mapping system. Moreover, the resulting shape and pose uncertainties, which we demonstrate can accurately reflect the true errors of our object maps, can also be useful for downstream robotics tasks such as active vision. We perform extensive evaluations on indoor and outdoor real-world datasets, achieving achieves substantial improvements over state-of-the-art methods. Our code will be available at https://github.com/TRAILab/UncertainShapePose.

The physical design process of large-scale designs is a time-consuming task, often requiring hours to days to complete, with routing being the most critical and complex step. As the the complexity of Integrated Circuits (ICs) increases, there is an increased demand for accurate routing quality prediction. Accurate congestion prediction aids in identifying design flaws early on, thereby accelerating circuit design and conserving resources. Despite the advancements in current congestion prediction methodologies, an essential aspect that has been largely overlooked is the spatial label-correlation between different grids in congestion prediction. The spatial label-correlation is a fundamental characteristic of circuit design, where the congestion status of a grid is not isolated but inherently influenced by the conditions of its neighboring grids. In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, {\ours}, i.e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids. {\ours} leverages variational inference techniques to estimate this weight, thereby enhancing the regression model's performance by incorporating spatial dependencies. Experiment results validate the superior effectiveness of {\ours} on the public available \texttt{ISPD2011} and \texttt{DAC2012} benchmarks using the superblue circuit line.