We present a Reinforcement Learning (RL) approach to the problem of controlling the Discontinuous Reception (DRX) policy from a Base Transceiver Station (BTS) in a cellular network. We do so by means of optimally timing the transmission of fast Layer-2 signaling messages (a.k.a. Medium Access Layer (MAC) Control Elements (CEs) as specified in 5G New Radio). Unlike more conventional approaches to DRX optimization, which rely on fine-tuning the values of DRX timers, we assess the gains that can be obtained solely by means of this MAC CE signalling. For the simulation part, we concentrate on traffic types typically encountered in Extended Reality (XR) applications, where the need for battery drain minimization and overheating mitigation are particularly pressing. Both 3GPP 5G New Radio (5G NR) compliant and non-compliant ("beyond 5G") MAC CEs are considered. Our simulation results show that our proposed technique strikes an improved trade-off between latency and energy savings as compared to conventional timer-based approaches that are characteristic of most current implementations. Specifically, our RL-based policy can nearly halve the active time for a single User Equipment (UE) with respect to a na\"ive MAC CE transmission policy, and still achieve near 20% active time reduction for 9 simultaneously served UEs.

Sixth-generation (6G) networks leverage simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) to overcome the limitations of traditional RISs. However, deploying STAR-RISs indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs) and STAR-RISs is proposed for indoor communication. An optimization problem encompassing user assignment, access point beamforming, and STAR-RIS phase control for reflection and transmission is formulated. The inherent complexity of the formulated problem necessitates a decomposition approach for an efficient solution. This involves tackling different sub-problems with specialized techniques: a many-to-one matching algorithm is employed to assign users to appropriate access points, optimizing resource allocation. To facilitate efficient resource management, access points are grouped using a correlation-based K-means clustering algorithm. Multi-agent deep reinforcement learning (MADRL) is leveraged to optimize the control of the STAR-RIS. Yu Min Park, Sheikh Salman Hassan, Eui-Nam Huh, and Choong Seon Hong are with the Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, Rep. of Korea, e-mails:{yumin0906, salman0335, johnhuh, cshong}@khu.ac.kr. Yan Kyaw Tun is with the Department of Electronic Systems, Aalborg University, A. C. Meyers Vænge 15, 2450 København, e-mail: ykt@es.aau.dk. Walid Saad is with the Bradley Department of Electrical and Computer Engineering, Virginia Tech, VA, 24061, USA. Additionally, the proposed MADRL approach incorporates convex approximation (CA).

Machine learning techniques applied to the problem of financial market forecasting struggle with dynamic regime switching, or underlying correlation and covariance shifts in true (hidden) market variables. Drawing inspiration from the success of reinforcement learning in robotics, particularly in agile locomotion adaptation of quadruped robots to unseen terrains, we introduce an innovative approach that leverages world knowledge of pretrained LLMs (aka. 'privileged information' in robotics) and dynamically adapts them using intrinsic, natural market rewards using LLM alignment technique we dub as "Reinforcement Learning from Market Feedback" (**RLMF**). Strong empirical results demonstrate the efficacy of our method in adapting to regime shifts in financial markets, a challenge that has long plagued predictive models in this domain. The proposed algorithmic framework outperforms best-performing SOTA LLM models on the existing (FLARE) benchmark stock-movement (SM) tasks by more than 15\% improved accuracy. On the recently proposed NIFTY SM task, our adaptive policy outperforms the SOTA best performing trillion parameter models like GPT-4. The paper details the dual-phase, teacher-student architecture and implementation of our model, the empirical results obtained, and an analysis of the role of language embeddings in terms of Information Gain.

We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. In this paper, we develop two algorithms for the infinite-horizon average reward setting. Our first algorithm \texttt{UCRL2-MNL} applies to the class of communicating MDPs and achieves an $\tilde{\mathcal{O}}(dD\sqrt{T})$ regret, where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horizon. The second algorithm \texttt{OVIFH-MNL} is computationally more efficient and applies to the more general class of weakly communicating MDPs, for which we show a regret guarantee of $\tilde{\mathcal{O}}(d^{2/5} \mathrm{sp}(v^*)T^{4/5})$ where $\mathrm{sp}(v^*)$ is the span of the associated optimal bias function. We also prove a lower bound of $\Omega(d\sqrt{DT})$ for learning communicating MDPs with MNL transitions of diameter at most $D$. Furthermore, we show a regret lower bound of $\Omega(dH^{3/2}\sqrt{K})$ for learning $H$-horizon episodic MDPs with MNL function approximation where $K$ is the number of episodes, which improves upon the best-known lower bound for the finite-horizon setting.

Generative Flow Networks (GFlowNets) treat sampling from distributions over compositional discrete spaces as a sequential decision-making problem, training a stochastic policy to construct objects step by step. Recent studies have revealed strong connections between GFlowNets and entropy-regularized reinforcement learning. Building on these insights, we propose to enhance planning capabilities of GFlowNets by applying Monte Carlo Tree Search (MCTS). Specifically, we show how the MENTS algorithm (Xiao et al., 2019) can be adapted for GFlowNets and used during both training and inference. Our experiments demonstrate that this approach improves the sample efficiency of GFlowNet training and the generation fidelity of pre-trained GFlowNet models.

With the rapid development of artificial intelligence technology, the field of reinforcement learning has continuously achieved breakthroughs in both theory and practice. However, traditional reinforcement learning algorithms often entail high energy consumption during interactions with the environment. Spiking Neural Network (SNN), with their low energy consumption characteristics and performance comparable to deep neural networks, have garnered widespread attention. To reduce the energy consumption of practical applications of reinforcement learning, researchers have successively proposed the Pop-SAN and MDC-SAN algorithms. Nonetheless, these algorithms use rectangular functions to approximate the spike network during the training process, resulting in low sensitivity, thus indicating room for improvement in the training effectiveness of SNN. Based on this, we propose a trapezoidal approximation gradient method to replace the spike network, which not only preserves the original stable learning state but also enhances the model's adaptability and response sensitivity under various signal dynamics. Simulation results show that the improved algorithm, using the trapezoidal approximation gradient to replace the spike network, achieves better convergence speed and performance compared to the original algorithm and demonstrates good training stability.

The short-loading cycle is a repetitive task performed in high quantities, making it a great alternative for automation. In the short-loading cycle, an expert operator navigates towards a pile, fills the bucket with material, navigates to a dump truck, and dumps the material into the tipping body. The operator has to balance the productivity goal while minimising the fuel usage, to maximise the overall efficiency of the cycle. In addition, difficult interactions, such as the tyre-to-surface interaction further complicate the cycle. These types of hard-to-model interactions that can be difficult to address with rule-based systems, together with the efficiency requirements, motivate us to examine the potential of data-driven approaches. In this paper, the possibility of teaching an agent through reinforcement learning to approach a dump truck's tipping body and get in position to dump material in the tipping body is examined. The agent is trained in a 3D simulated environment to perform a simplified navigation task. The trained agent is directly transferred to a real vehicle, to perform the same task, with no additional training. The results indicate that the agent can successfully learn to navigate towards the dump truck with a limited amount of control signals in simulation and when transferred to a real vehicle, exhibits the correct behaviour.

Despite advancements in robotic-assisted surgery, automating complex tasks like suturing remain challenging due to the need for adaptability and precision. Learning-based approaches, particularly reinforcement learning (RL) and imitation learning (IL), require realistic simulation environments for efficient data collection. However, current platforms often include only relatively simple, non-dexterous manipulations and lack the flexibility required for effective learning and generalization. We introduce SurgicAI, a novel platform for development and benchmarking addressing these challenges by providing the flexibility to accommodate both modular subtasks and more importantly task decomposition in RL-based surgical robotics. Compatible with the da Vinci Surgical System, SurgicAI offers a standardized pipeline for collecting and utilizing expert demonstrations. It supports deployment of multiple RL and IL approaches, and the training of both singular and compositional subtasks in suturing scenarios, featuring high dexterity and modularization. Meanwhile, SurgicAI sets clear metrics and benchmarks for the assessment of learned policies. We implemented and evaluated multiple RL and IL algorithms on SurgicAI. Our detailed benchmark analysis underscores SurgicAI's potential to advance policy learning in surgical robotics. Details: \url{https://github.com/surgical-robotics-ai/SurgicAI

Mobile robots operating in crowded environments require the ability to navigate among humans and surrounding obstacles efficiently while adhering to safety standards and socially compliant mannerisms. This scale of the robot navigation problem may be classified as both a local path planning and trajectory optimization problem. This work presents an array of force sensors that act as a tactile layer to complement the use of a LiDAR for the purpose of inducing awareness of contact with any surrounding objects within immediate vicinity of a mobile robot undetected by LiDARs. By incorporating the tactile layer, the robot can take more risks in its movements and possibly go right up to an obstacle or wall, and gently squeeze past it. In addition, we built up a simulation platform via Pybullet which integrates Robot Operating System (ROS) and reinforcement learning (RL) together. A touch-aware neural network model was trained on it to create an RL-based local path planner for dynamic obstacle avoidance. Our proposed method was demonstrated successfully on an omni-directional mobile robot who was able to navigate in a crowded environment with high agility and versatility in movement, while not being overly sensitive to nearby obstacles-not-in-contact.

Sequential decision-making can be formulated as a text-conditioned video generation problem, where a video planner, guided by a text-defined goal, generates future frames visualizing planned actions, from which control actions are subsequently derived. In this work, we introduce Active Region Video Diffusion for Universal Policies (ARDuP), a novel framework for video-based policy learning that emphasizes the generation of active regions, i.e. potential interaction areas, enhancing the conditional policy's focus on interactive areas critical for task execution. This innovative framework integrates active region conditioning with latent diffusion models for video planning and employs latent representations for direct action decoding during inverse dynamic modeling. By utilizing motion cues in videos for automatic active region discovery, our method eliminates the need for manual annotations of active regions. We validate ARDuP's efficacy via extensive experiments on simulator CLIPort and the real-world dataset BridgeData v2, achieving notable improvements in success rates and generating convincingly realistic video plans.