Tabular average reward Temporal Difference (TD) learning is perhaps the simplest and the most fundamental policy evaluation algorithm in average reward reinforcement learning. After at least 25 years since its discovery, we are finally able to provide a long-awaited almost sure convergence analysis. Namely, we are the first to prove that, under very mild conditions, tabular average reward TD converges almost surely to a sample path dependent fixed point. Key to this success is a new general stochastic approximation result concerning nonexpansive mappings with Markovian and additive noise, built on recent advances in stochastic Krasnoselskii-Mann iterations.

Two-stage object detectors exhibit high accuracy and precise localization, especially for identifying small objects that are favorable for various edge applications. However, the high computation costs associated with two-stage detection methods cause more severe thermal issues on edge devices, incurring dynamic runtime frequency change and thus large inference latency variations. Furthermore, the dynamic number of proposals in different frames leads to various computations over time, resulting in further latency variations. The significant latency variations of detectors on edge devices can harm user experience and waste hardware resources. To avoid thermal throttling and provide stable inference speed, we propose Lotus, a novel framework that is tailored for two-stage detectors to dynamically scale CPU and GPU frequencies jointly in an online manner based on deep reinforcement learning (DRL). To demonstrate the effectiveness of Lotus, we implement it on NVIDIA Jetson Orin Nano and Mi 11 Lite mobile platforms. The results indicate that Lotus can consistently and significantly reduce latency variation, achieve faster inference, and maintain lower CPU and GPU temperatures under various settings.

Navigation is a fundamental cognitive skill extensively studied in neuroscientific experiments and has lately gained substantial interest in artificial intelligence research. Recreating the task solved by rodents in the well-established Morris Water Maze (MWM) experiment, this work applies a transformer-based architecture using deep reinforcement learning -- an approach previously unexplored in this context -- to navigate a 2D version of the maze. Specifically, the agent leverages a decoder-only transformer architecture serving as a deep Q-network performing effective decision making in the partially observable environment. We demonstrate that the proposed architecture enables the agent to efficiently learn spatial navigation strategies, overcoming challenges associated with a limited field of vision, corresponding to the visual information available to a rodent in the MWM. Demonstrating the potential of transformer-based models for enhancing navigation performance in partially observable environments, this work suggests promising avenues for future research in artificial agents whose behavior resembles that of biological agents. Finally, the flexibility of the transformer architecture in supporting varying input sequence lengths opens opportunities for gaining increased understanding of the artificial agent's inner representation of the environment.

Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise constraints in expectation or enforce hard state-wise constraints with strong assumptions. The former does not exclude the probability of safety violations, while the latter is impractical. Our insight is that although it is intractable to guarantee hard state-wise constraints in a model-free setting, we can enforce state-wise safety with high probability while excluding strong assumptions. To accomplish the goal, we propose Absolute State-wise Constrained Policy Optimization (ASCPO), a novel general-purpose policy search algorithm that guarantees high-probability state-wise constraint satisfaction for stochastic systems. We demonstrate the effectiveness of our approach by training neural network policies for extensive robot locomotion tasks, where the agent must adhere to various state-wise safety constraints. Our results show that ASCPO significantly outperforms existing methods in handling state-wise constraints across challenging continuous control tasks, highlighting its potential for real-world applications.

In cross-device federated learning (FL) with millions of mobile clients, only a small subset of clients participate in training in every communication round, and Federated Averaging (FedAvg) is the most popular algorithm in practice. Existing analyses of FedAvg usually assume the participating clients are independently sampled in each round from a uniform distribution, which does not reflect real-world scenarios. This paper introduces a theoretical framework that models client participation in FL as a Markov chain to study optimization convergence when clients have non-uniform and correlated participation across rounds. We apply this framework to analyze a more general and practical pattern: every client must wait a minimum number of $R$ rounds (minimum separation) before re-participating. We theoretically prove and empirically observe that increasing minimum separation reduces the bias induced by intrinsic non-uniformity of client availability in cross-device FL systems. Furthermore, we develop an effective debiasing algorithm for FedAvg that provably converges to the unbiased optimal solution under arbitrary minimum separation and unknown client availability distribution.

Embodied AI is a rapidly advancing field that bridges the gap between cyberspace and physical space, enabling a wide range of applications. This evolution has led to the development of the Vehicular Embodied AI NETwork (VEANET), where advanced AI capabilities are integrated into vehicular systems to enhance autonomous operations and decision-making. Embodied agents, such as Autonomous Vehicles (AVs), are autonomous entities that can perceive their environment and take actions to achieve specific goals, actively interacting with the physical world. Embodied twins are digital models of these embodied agents, with various embodied AI twins for intelligent applications in cyberspace. In VEANET, embodied AI twins act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving using generative AI models. Due to limited computational resources of AVs, these AVs often offload computationally intensive tasks, such as constructing and updating embodied AI twins, to nearby RSUs. However, since the rapid mobility of AVs and the limited provision coverage of a single RSU, embodied AI twins require dynamic migrations from current RSU to other RSUs in real-time, resulting in the challenge of selecting suitable RSUs for efficient embodied AI twins migrations. Given information asymmetry, AVs cannot know the detailed information of RSUs. To this end, in this paper, we construct a multi-dimensional contract theoretical model between AVs and alternative RSUs. Considering that AVs may exhibit irrational behavior, we utilize prospect theory instead of expected utility theory to model the actual utilities of AVs. Finally, we employ a generative diffusion model-based algorithm to identify the optimal contract designs. Compared with traditional deep reinforcement learning algorithms, numerical results demonstrate the effectiveness of the proposed scheme.

Robotic tasks often require multiple manipulators to enhance task efficiency and speed, but this increases complexity in terms of collaboration, collision avoidance, and the expanded state-action space. To address these challenges, we propose a multi-level approach combining Reinforcement Learning (RL) and Dynamic Movement Primitives (DMP) to generate adaptive, real-time trajectories for new tasks in dynamic environments using a demonstration library. This method ensures collision-free trajectory generation and efficient collaborative motion planning. We validate the approach through experiments in the PyBullet simulation environment with UR5e robotic manipulators.

Learning agents with reinforcement learning is difficult when dealing with long trajectories that involve a large number of states. To address these learning problems effectively, the number of states can be reduced by abstract representations that cluster states. In principle, deep reinforcement learning can find abstract states, but end-to-end learning is unstable. We propose contrastive abstraction learning to find abstract states, where we assume that successive states in a trajectory belong to the same abstract state. Such abstract states may be basic locations, achieved subgoals, inventory, or health conditions. Contrastive abstraction learning first constructs clusters of state representations by contrastive learning and then applies modern Hopfield networks to determine the abstract states. The first phase of contrastive abstraction learning is self-supervised learning, where contrastive learning forces states with sequential proximity to have similar representations. The second phase uses modern Hopfield networks to map similar state representations to the same fixed point, i.e.\ to an abstract state. The level of abstraction can be adjusted by determining the number of fixed points of the modern Hopfield network. Furthermore, \textit{contrastive abstraction learning} does not require rewards and facilitates efficient reinforcement learning for a wide range of downstream tasks. Our experiments demonstrate the effectiveness of contrastive abstraction learning for reinforcement learning.

Traditional reinforcement learning often struggles to generate diverse, high-reward solutions, especially in domains like drug design and black-box function optimization. Markov Chain Monte Carlo (MCMC) methods provide an alternative method of RL in candidate selection but suffer from high computational costs and limited candidate diversity exploration capabilities. In response, GFlowNet, a novel neural network architecture, was introduced to model complex system dynamics and generate diverse high-reward trajectories. To further enhance this approach, this paper proposes improvements to GFlowNet by introducing a new loss function and refining the training objective associated with sub-GFlowNet. These enhancements aim to integrate entropy and leverage network structure characteristics, improving both candidate diversity and computational efficiency. We demonstrated the superiority of the refined GFlowNet over traditional methods by empirical results from hypergrid experiments and molecule synthesis tasks. The findings underscore the effectiveness of incorporating entropy and exploiting network structure properties in solution generation in molecule synthesis as well as diverse experimental designs.

Simulation has enabled unprecedented compute-scalable approaches to robot learning. However, many existing simulation frameworks typically support a narrow range of scenes/tasks and lack features critical for scaling generalizable robotics and sim2real. We introduce and open source ManiSkill3, the fastest state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation. ManiSkill3 supports GPU parallelization of many aspects including simulation+rendering, heterogeneous simulation, pointclouds/voxels visual input, and more. Simulation with rendering on ManiSkill3 can run 10-1000x faster with 2-3x less GPU memory usage than other platforms, achieving up to 30,000+ FPS in benchmarked environments due to minimal python/pytorch overhead in the system, simulation on the GPU, and the use of the SAPIEN parallel rendering system. Tasks that used to take hours to train can now take minutes. We further provide the most comprehensive range of GPU parallelized environments/tasks spanning 12 distinct domains including but not limited to mobile manipulation for tasks such as drawing, humanoids, and dextrous manipulation in realistic scenes designed by artists or real-world digital twins. In addition, millions of demonstration frames are provided from motion planning, RL, and teleoperation. ManiSkill3 also provides a comprehensive set of baselines that span popular RL and learning-from-demonstrations algorithms.