Solar sensor-based monitoring systems have become a crucial agricultural innovation, advancing farm management and animal welfare through integrating sensor technology, Internet-of-Things, and edge and cloud computing. However, the resilience of these systems to cyber-attacks and their adaptability to dynamic and constrained energy supplies remain largely unexplored. To address these challenges, we propose a sustainable smart farm network designed to maintain high-quality animal monitoring under various cyber and adversarial threats, as well as fluctuating energy conditions. Our approach utilizes deep reinforcement learning (DRL) to devise optimal policies that maximize both monitoring effectiveness and energy efficiency. To overcome DRL's inherent challenge of slow convergence, we integrate transfer learning (TL) and decision theory (DT) to accelerate the learning process. By incorporating DT-guided strategies, we optimize monitoring quality and energy sustainability, significantly reducing training time while achieving comparable performance rewards. Our experimental results prove that DT-guided DRL outperforms TL-enhanced DRL models, improving system performance and reducing training runtime by 47.5%.

This paper introduces a novel framework integrating nonlinear acoustic computing and reinforcement learning to enhance advanced human-robot interaction under complex noise and reverberation. Leveraging physically informed wave equations (e.g., Westervelt, KZK), the approach captures higher-order phenomena such as harmonic generation and shock formation. By embedding these models in a reinforcement learning-driven control loop, the system adaptively optimizes key parameters (e.g., absorption, beamforming) to mitigate multipath interference and non-stationary noise. Experimental evaluations, covering far-field localization, weak signal detection, and multilingual speech recognition, demonstrate that this hybrid strategy surpasses traditional linear methods and purely data-driven baselines, achieving superior noise suppression, minimal latency, and robust accuracy in demanding real-world scenarios. The proposed system demonstrates broad application prospects in AI hardware, robot, machine audition, artificial audition, and brain-machine interfaces.

Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work has successfully learned an $ε$-optimal policy with a sample complexity of $O(1/ε^2)$ trajectories with general function approximation when strategic exploration is necessary. We address this open problem by introducing a novel actor-critic algorithm that attains a sample-complexity of $O(dH^5 \log|\mathcal{A}|/ε^2 + d H^4 \log|\mathcal{F}|/ ε^2)$ trajectories, and accompanying $\sqrt{T}$ regret when the Bellman eluder dimension $d$ does not increase with $T$ at more than a $\log T$ rate. Here, $\mathcal{F}$ is the critic function class, $\mathcal{A}$ is the action space, and $H$ is the horizon in the finite horizon MDP setting. Our algorithm integrates optimism, off-policy critic estimation targeting the optimal Q-function, and rare-switching policy resets. We extend this to the setting of Hybrid RL, showing that initializing the critic with offline data yields sample efficiency gains compared to purely offline or online RL. Further, utilizing access to offline data, we provide a \textit{non-optimistic} provably efficient actor-critic algorithm that only additionally requires $N_{\text{off}} \geq c_{\text{off}}^*dH^4/ε^2$ in exchange for omitting optimism, where $c_{\text{off}}^*$ is the single-policy concentrability coefficient and $N_{\text{off}}$ is the number of offline samples. This addresses another open problem in the literature. We further provide numerical experiments to support our theoretical findings.

Judicious resource allocation can effectively enhance federated learning (FL) training performance in wireless networks by addressing both system and statistical heterogeneity. However, existing strategies typically rely on block fading assumptions, which overlooks rapid channel fluctuations within each round of FL gradient uploading, leading to a degradation in FL training performance. Therefore, this paper proposes a small-scale-fading-aware resource allocation strategy using a multi-agent reinforcement learning (MARL) framework. Specifically, we establish a one-step convergence bound of the FL algorithm and formulate the resource allocation problem as a decentralized partially observable Markov decision process (Dec-POMDP), which is subsequently solved using the QMIX algorithm. In our framework, each client serves as an agent that dynamically determines spectrum and power allocations within each coherence time slot, based on local observations and a reward derived from the convergence analysis. The MARL setting reduces the dimensionality of the action space and facilitates decentralized decision-making, enhancing the scalability and practicality of the solution. Experimental results demonstrate that our QMIX-based resource allocation strategy significantly outperforms baseline methods across various degrees of statistical heterogeneity. Additionally, ablation studies validate the critical importance of incorporating small-scale fading dynamics, highlighting its role in optimizing FL performance.

Reinforcement Learning (RL) has shown great potential in complex control tasks, particularly when combined with deep neural networks within the Actor-Critic (AC) framework. However, in practical applications, balancing exploration, learning stability, and sample efficiency remains a significant challenge. Traditional methods such as Soft Actor-Critic (SAC) and Proximal Policy Optimization (PPO) address these issues by incorporating entropy or relative entropy regularization, but often face problems of instability and low sample efficiency. In this paper, we propose the Conservative Soft Actor-Critic (CSAC) algorithm, which seamlessly integrates entropy and relative entropy regularization within the AC framework. CSAC improves exploration through entropy regularization while avoiding overly aggressive policy updates with the use of relative entropy regularization. Evaluations on benchmark tasks and real-world robotic simulations demonstrate that CSAC offers significant improvements in stability and efficiency over existing methods. These findings suggest that CSAC provides strong robustness and application potential in control tasks under dynamic environments.

Figure 1: AMO enables hyper-dexterous whole-body movements for humanoid robots. Abstract --Humanoid robots derive much of their dexterity from hyper-dexterous whole-body movements, enabling tasks that require a large operational workspace--such as picking objects off the ground. However, achieving these capabilities on real humanoids remains challenging due to their high degrees of freedom (DoF) and nonlinear dynamics. We propose Adaptive Motion Optimization (AMO), a framework that integrates sim-to-real reinforcement learning (RL) with trajectory optimization for real-time, adaptive whole-body control. We validate AMO in simulation and on a 29-DoF Unitree G1 humanoid robot, demonstrating superior stability and an expanded workspace compared to strong baselines. Finally, we show that AMO's consistent performance supports autonomous task execution via imitation learning, underscoring the system's versatility and robustness. Humans can expand their workspace of hands using whole-body movements. The joint configurations of humanoid robots closely mimic humans' functionality and degree of freedom while facing challenges of achieving similar movements with Metrics AMO (Ours) HOVER [30] Opt2Skill [41] Ref. Type Hybrid MoCap Traj. T orso means if the robot is able to adjust its' torso's orientation and height to expand the workspace.

Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample efficiency, and poor model interpretability. Inspired by the strong reasoning abilities of large language models (LLMs), we propose a novel strategy-based reinforcement learning framework integrated with LLMs called DYnamic STrategy Induction with Llms for reinforcement learning (DYSTIL) to overcome these limitations. DYSTIL dynamically queries a strategy-generating LLM to induce textual strategies based on advantage estimations and expert demonstrations, and gradually internalizes induced strategies into the RL agent through policy optimization to improve its performance through boosting policy generalization and enhancing sample efficiency. It also provides a direct textual channel to observe and interpret the evolution of the policy's underlying strategies during training. We test DYSTIL over challenging RL environments from Minigrid and BabyAI, and empirically demonstrate that DYSTIL significantly outperforms state-of-the-art baseline methods by 17.75% in average success rate while also enjoying higher sample efficiency during the learning process.

The Markov Decision Process (MDP) is a popular framework for sequential decision-making problems, and uncertainty quantification is an essential component of it to learn optimal decision-making strategies. In particular, a Bayesian framework is used to maintain beliefs about the optimal decisions and the unknown ingredients of the model, which are also to be learned from the data, such as the rewards and state dynamics. However, many existing Bayesian approaches for learning the optimal decision-making strategy are based on unrealistic modelling assumptions and utilise approximate inference techniques. This raises doubts whether the benefits of Bayesian uncertainty quantification are fully realised or can be relied upon. We focus on infinite-horizon and undiscounted MDPs, with finite state and action spaces, and a terminal state. We provide a full Bayesian framework, from modelling to inference to decision-making. For modelling, we introduce a likelihood function with minimal assumptions for learning the optimal action-value function based on Bellman's optimality equations, analyse its properties, and clarify connections to existing works. For deterministic rewards, the likelihood is degenerate and we introduce artificial observation noise to relax it, in a controlled manner, to facilitate more efficient Monte Carlo-based inference. For inference, we propose an adaptive sequential Monte Carlo algorithm to both sample from and adjust the sequence of relaxed posterior distributions. For decision-making, we choose actions using samples from the posterior distribution over the optimal strategies. While commonly done, we provide new insight that clearly shows that it is a generalisation of Thompson sampling from multi-arm bandit problems. Finally, we evaluate our framework on the Deep Sea benchmark problem and demonstrate the exploration benefits of posterior sampling in MDPs.

We establish a continuous-time framework for analyzing Deep Q-Networks (DQNs) via stochastic control and Forward-Backward Stochastic Differential Equations (FBSDEs). Considering a continuous-time Markov Decision Process (MDP) driven by a square-integrable martingale, we analyze DQN approximation properties. We show that DQNs can approximate the optimal Q-function on compact sets with arbitrary accuracy and high probability, leveraging residual network approximation theorems and large deviation bounds for the state-action process. We then analyze the convergence of a general Q-learning algorithm for training DQNs in this setting, adapting stochastic approximation theorems. Our analysis emphasizes the interplay between DQN layer count, time discretization, and the role of viscosity solutions (primarily for the value function $V^*$) in addressing potential non-smoothness of the optimal Q-function. This work bridges deep reinforcement learning and stochastic control, offering insights into DQNs in continuous-time settings, relevant for applications with physical systems or high-frequency data.

-- Building models responsive to input prompts represents a transformative shift in machine learning. This paradigm holds significant potential for robotics problems, such as targeted manipulation amidst clutter . In this work, we present a novel approach to combine promptable foundation models with reinforcement learning (RL), enabling robots to perform dexterous manipulation tasks in a prompt-responsive manner . Existing methods struggle to link high-level commands with fine-grained dexterous control. We address this gap with a memory-augmented student-teacher learning framework. We use the Segment-Anything 2 (SAM 2) model as a perception backbone to infer an object of interest from user prompts. While detections are imperfect, their temporal sequence provides rich information for implicit state estimation by memory-augmented models. Our approach successfully learns prompt-responsive policies, demonstrated in picking objects from cluttered scenes.