Reinforcement learning (RL) is widely used in applications where one needs to perform sequential decision-making while interacting with the environment. The standard RL problem with safety constraints is generally mathematically modeled by constrained Markov Decision Processes (CMDP), which is linear in objective and rules in occupancy measure space, where the problem becomes challenging in the case where the model is unknown apriori. The problem further becomes challenging when the decision requirement includes optimizing a concave utility while satisfying some nonlinear safety constraints. To solve such a nonlinear problem, we propose a conservative stochastic primal-dual algorithm (CSPDA) via a randomized primal-dual approach. By leveraging a generative model, we prove that CSPDA not only exhibits Õ(1/ε2)sample complexity, but also achieves zero constraint violations for the concave utility CMDP. Compared with the previous works, the best available sample complexity for CMDP with zero constraint violation is Õ(1/ε5). Hence, the proposed algorithm provides a significant improvement as compared to the state-of-the-art.

The promotion of large-scale applications of reinforcement learning (RL) requires efficient training computation. While existing parallel RL frameworks encompass a variety of RL algorithms and parallelization techniques, the excessively burdensome communication frameworks hinder the attainment of the hardware's limit for final throughput and training effects on a single desktop. In this paper, we propose Spreeze, a lightweight parallel framework for RL that efficiently utilizes a single desktop hardware resource to approach the throughput limit. We asynchronously parallelize the experience sampling, network update, performance evaluation, and visualization operations, and employ multiple efficient data transmission techniques to transfer various types of data between processes. The framework can automatically adjust the parallelization hyperparameters based on the computing ability of the hardware device in order to perform efficient large-batch updates. Based on the characteristics of the "Actor-Critic" RL algorithm, our framework uses dual GPUs to independently update the network of actors and critics in order to further improve throughput. Simulation results show that our framework can achieve up to 15,000Hz experience sampling and 370,000Hz network update frame rate using only a personal desktop computer, which is an order of magnitude higher than other mainstream parallel RL frameworks, resulting in a 73% reduction of training time. Our work on fully utilizing the hardware resources of a single desktop computer is fundamental to enabling efficient large-scale distributed RL training.

Cooperative autonomous driving plays a pivotal role in improving road capacity and safety within intelligent transportation systems, particularly through the deployment of autonomous vehicles on urban streets. By enabling vehicle-to-vehicle communication, these systems expand the vehicles environmental awareness, allowing them to detect hidden obstacles and thereby enhancing safety and reducing crash rates compared to human drivers who rely solely on visual perception. A key application of this technology is vehicle platooning, where connected vehicles drive in a coordinated formation. This paper introduces a vehicle platooning approach designed to enhance traffic flow and safety. Developed using deep reinforcement learning in the Unity 3D game engine, known for its advanced physics, this approach aims for a high-fidelity physical simulation that closely mirrors real-world conditions. The proposed platooning model focuses on scalability, decentralization, and fostering positive cooperation through the introduced predecessor-follower "sharing and caring" communication framework. The study demonstrates how these elements collectively enhance autonomous driving performance and robustness, both for individual vehicles and for the platoon as a whole, in an urban setting. This results in improved road safety and reduced traffic congestion.

This paper introduces a novel approach for learning polynomial representations of physical objects. Given a point cloud data set associated with a physical object, we solve a one-class classification problem to bound the data points by a polynomial sublevel set while harnessing Sum-of-Squares (SOS) programming to enforce prior shape knowledge constraints. By representing objects as polynomial sublevel sets we further show it is possible to construct a secondary SOS program to certify whether objects are packed correctly, that is object boundaries do not overlap and are inside some container set. While not employing reinforcement learning (RL) in this work, our proposed secondary SOS program does provide a potential surrogate reward function for RL algorithms, autonomously rewarding agents that propose object rotations and translations that correctly pack objects within a given container set.

Offline meta-reinforcement learning (meta-RL) methods, which adapt to unseen target tasks with prior experience, are essential in robot control tasks. Current methods typically utilize task contexts and skills as prior experience, where task contexts are related to the information within each task and skills represent a set of temporally extended actions for solving subtasks. However, these methods still suffer from limited performance when adapting to unseen target tasks, mainly because the learned prior experience lacks generalization, i.e., they are unable to extract effective prior experience from meta-training tasks by exploration and learning of continuous latent spaces. We propose a framework called decoupled meta-reinforcement learning (DCMRL), which (1) contrastively restricts the learning of task contexts through pulling in similar task contexts within the same task and pushing away different task contexts of different tasks, and (2) utilizes a Gaussian quantization variational autoencoder (GQ-VAE) for clustering the Gaussian distributions of the task contexts and skills respectively, and decoupling the exploration and learning processes of their spaces. These cluster centers which serve as representative and discrete distributions of task context and skill are stored in task context codebook and skill codebook, respectively. DCMRL can acquire generalizable prior experience and achieve effective adaptation to unseen target tasks during the meta-testing phase. Experiments in the navigation and robot manipulation continuous control tasks show that DCMRL is more effective than previous meta-RL methods with more generalizable prior experience.

Combining gradient-based trajectory optimization with differentiable physics simulation is an efficient technique for solving soft-body manipulation problems. Using a well-crafted optimization objective, the solver can quickly converge onto a valid trajectory. However, writing the appropriate objective functions requires expert knowledge, making it difficult to collect a large set of naturalistic problems from non-expert users. We introduce DiffVL, a method that enables non-expert users to communicate soft-body manipulation tasks -- a combination of vision and natural language, given in multiple stages -- that can be readily leveraged by a differential physics solver. We have developed GUI tools that enable non-expert users to specify 100 tasks inspired by real-life soft-body manipulations from online videos, which we'll make public. We leverage large language models to translate task descriptions into machine-interpretable optimization objectives. The optimization objectives can help differentiable physics solvers to solve these long-horizon multistage tasks that are challenging for previous baselines.

In this paper, we address the issue of increasing the performance of reinforcement learning (RL) solutions for autonomous racing cars when navigating under conditions where practical vehicle modelling errors (commonly known as \emph{model mismatches}) are present. To address this challenge, we propose a partial end-to-end algorithm that decouples the planning and control tasks. Within this framework, an RL agent generates a trajectory comprising a path and velocity, which is subsequently tracked using a pure pursuit steering controller and a proportional velocity controller, respectively. In contrast, many current learning-based (i.e., reinforcement and imitation learning) algorithms utilise an end-to-end approach whereby a deep neural network directly maps from sensor data to control commands. By leveraging the robustness of a classical controller, our partial end-to-end driving algorithm exhibits better robustness towards model mismatches than standard end-to-end algorithms.

Various works have utilized deep reinforcement learning (DRL) to address the query optimization problem in database system. They either learn to construct plans from scratch in a bottom-up manner or guide the plan generation behavior of traditional optimizer using hints. While these methods have achieved some success, they face challenges in either low training efficiency or limited plan search space. To address these challenges, we introduce FOSS, a novel DRL-based framework for query optimization. FOSS initiates optimization from the original plan generated by a traditional optimizer and incrementally refines suboptimal nodes of the plan through a sequence of actions. Additionally, we devise an asymmetric advantage model to evaluate the advantage between two plans. We integrate it with a traditional optimizer to form a simulated environment. Leveraging this simulated environment, FOSS can bootstrap itself to rapidly generate a large amount of high-quality simulated experiences. FOSS then learns and improves its optimization capability from these simulated experiences. We evaluate the performance of FOSS on Join Order Benchmark, TPC-DS, and Stack Overflow. The experimental results demonstrate that FOSS outperforms the state-of-the-art methods in terms of latency performance and optimization time. Compared to PostgreSQL, FOSS achieves savings ranging from 15% to 83% in total latency across different benchmarks.

Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy measures to obtain a surrogate reward for forward reinforcement learning. However, the traditional discriminator is a simple binary classifier and doesn't learn an accurate distribution, which may result in failing to identify expert-level state-action pairs induced by the policy interacting with the environment. To address this issue, we propose a method named diffusion adversarial imitation learning (DiffAIL), which introduces the diffusion model into the AIL framework. Specifically, DiffAIL models the state-action pairs as unconditional diffusion models and uses diffusion loss as part of the discriminator's learning objective, which enables the discriminator to capture better expert demonstrations and improve generalization. Experimentally, the results show that our method achieves state-of-the-art performance and significantly surpasses expert demonstration on two benchmark tasks, including the standard state-action setting and state-only settings. Our code can be available at the link https://github.com/ML-Group-SDU/DiffAIL.

The Metaverse is gaining attention among academics as maturing technologies empower the promises and envisagements of a multi-purpose, integrated virtual environment. An interactive and immersive socialization experience between people is one of the promises of the Metaverse. In spite of the rapid advancements in current technologies, the computation required for a smooth, seamless and immersive socialization experience in the Metaverse is overbearing, and the accumulated user experience is essential to be considered. The computation burden calls for computation offloading, where the integration of virtual and physical world scenes is offloaded to an edge server. This paper introduces a novel Quality-of-Service (QoS) model for the accumulated experience in multi-user socialization on a multichannel wireless network. This QoS model utilizes deep reinforcement learning approaches to find the near-optimal channel resource allocation. Comprehensive experiments demonstrate that the adoption of the QoS model enhances the overall socialization experience.