On-device control agents, especially on mobile devices, are responsible for operating mobile devices to fulfill users' requests, enabling seamless and intuitive interactions. Integrating Multimodal Large Language Models (MLLMs) into these agents enhances their ability to understand and execute complex commands, thereby improving user experience. However, fine-tuning MLLMs for on-device control presents significant challenges due to limited data availability and inefficient online training processes. This paper introduces DistRL, a novel framework designed to enhance the efficiency of online RL fine-tuning for mobile device control agents. DistRL employs centralized training and decentralized data acquisition to ensure efficient fine-tuning in the context of dynamic online interactions. Additionally, the framework is backed by our tailor-made RL algorithm, which effectively balances exploration with the prioritized utilization of collected data to ensure stable and robust training. Our experiments show that, on average, DistRL delivers a 3X improvement in training efficiency and enables training data collection 2.4X faster than the leading synchronous multi-machine methods. Notably, after training, DistRL achieves a 20% relative improvement in success rate compared to state-of-the-art methods on general Android tasks from an open benchmark, significantly outperforming existing approaches while maintaining the same training time. These results validate DistRL as a scalable and efficient solution, offering substantial improvements in both training efficiency and agent performance for real-world, in-the-wild device control tasks.

Many organisms and cell types, from bacteria to cancer cells, exhibit a remarkable ability to adapt to fluctuating environments. Additionally, cells can leverage memory of past environments to better survive previously-encountered stressors. From a control perspective, this adaptability poses significant challenges in driving cell populations toward extinction, and is thus an open question with great clinical significance. In this work, we focus on drug dosing in cell populations exhibiting phenotypic plasticity. For specific dynamical models switching between resistant and susceptible states, exact solutions are known. However, when the underlying system parameters are unknown, and for complex memory-based systems, obtaining the optimal solution is currently intractable. To address this challenge, we apply reinforcement learning (RL) to identify informed dosing strategies to control cell populations evolving under novel non-Markovian dynamics. We find that model-free deep RL is able to recover exact solutions and control cell populations even in the presence of long-range temporal dynamics.

Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attention mechanism is incorporated into the actor and critic networks to automatically detect faults and dynamically regulate the attention given to faulty agents. Additionally, a prioritization mechanism is introduced to selectively sample transitions critical to current training needs. To further support research in this area, we design and open-source a highly decoupled code platform for fault-tolerant MARL, aimed at improving the efficiency of studying related problems. Experimental results demonstrate the effectiveness of our method in handling various types of faults, faults occurring in any agent, and faults arising at random times.

Building operations consume approximately 40% of global energy, with Heating, Ventilation, and Air Conditioning (HVAC) systems responsible for up to 50% of this consumption. As HVAC energy demands are expected to rise, optimising system efficiency is crucial for reducing future energy use and mitigating climate change. Existing control strategies lack generalisation and require extensive training and data, limiting their rapid deployment across diverse buildings. This paper introduces HVAC-DPT, a Decision-Pretrained Transformer using in-context Reinforcement Learning (RL) for multi-zone HVAC control. HVAC-DPT frames HVAC control as a sequential prediction task, training a causal transformer on interaction histories generated by diverse RL agents. This approach enables HVAC-DPT to refine its policy in-context, without modifying network parameters, allowing for deployment across different buildings without the need for additional training or data collection. HVAC-DPT reduces energy consumption in unseen buildings by 45% compared to the baseline controller, offering a scalable and effective approach to mitigating the increasing environmental impact of HVAC systems.

Despite recent advances in learning-based behavioral planning for autonomous systems, decision-making in multi-task missions remains a challenging problem. For instance, a mission might require a robot to explore an unknown environment, locate the goals, and navigate to them, even if there are obstacles along the way. Such problems are difficult to solve due to: a) sparse rewards, meaning a reward signal is available only once all the tasks in a mission have been satisfied, and b) the agent having to perform tasks at run-time that are not covered in the training data, e.g., demonstrations only from an environment where all doors were unlocked. Consequently, state-of-the-art decision-making methods in such settings are limited to missions where the required tasks are well-represented in the training demonstrations and can be solved within a short planning horizon. To overcome these limitations, we propose Adaptformer, a stochastic and adaptive planner that utilizes sequence models for sample-efficient exploration and exploitation. This framework relies on learning an energy-based heuristic, which needs to be minimized over a sequence of high-level decisions. To generate successful action sequences for long-horizon missions, Adaptformer aims to achieve shorter sub-goals, which are proposed through an intrinsic sub-goal curriculum. Through these two key components, Adaptformer allows for generalization to out-of-distribution tasks and environments, i.e., missions that were not a part of the training data. Empirical results in multiple simulation environments demonstrate the effectiveness of our method. Notably, Adaptformer not only outperforms the state-of-the-art method by up to 25% in multi-goal maze reachability tasks but also successfully adapts to multi-task missions that the state-of-the-art method could not complete, leveraging demonstrations from single-goal-reaching tasks.

Planning safe and efficient trajectories through signal-free intersections presents significant challenges for autonomous vehicles (AVs), particularly in dynamic, multi-task environments with unpredictable interactions and an increased possibility of conflicts. This study aims to address these challenges by developing a robust, adaptive framework to ensure safety in such complex scenarios. Existing approaches often struggle to provide reliable safety mechanisms in dynamic and learn multi-task behaviors from demonstrations in signal-free intersections. This study proposes a safety-critical planning method that integrates Dynamic High-Order Control Barrier Functions (DHOCBF) with a diffusion-based model, called Dynamic Safety-Critical Diffuser (DSC-Diffuser), offering a robust solution for adaptive, safe, and multi-task driving in signal-free intersections. Our approach incorporates a goal-oriented, task-guided diffusion model, enabling the model to learn multiple driving tasks simultaneously from real-world data. To further ensure driving safety in dynamic environments, the proposed DHOCBF framework dynamically adjusts to account for the movements of surrounding vehicles, offering enhanced adaptability compared to traditional control barrier functions. Validity evaluations of DHOCBF, conducted through numerical simulations, demonstrate its robustness in adapting to variations in obstacle velocities, sizes, uncertainties, and locations, effectively maintaining driving safety across a wide range of complex and uncertain scenarios. Performance evaluations across various scenes confirm that DSC-Diffuser provides realistic, stable, and generalizable policies, equipping it with the flexibility to adapt to diverse driving tasks.

Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose CAREL (Cross-modal Auxiliary REinforcement Learning) as a new framework to solve this problem using auxiliary loss functions inspired by video-text retrieval literature and a novel method called instruction tracking, which automatically keeps track of progress in an environment. The results of our experiments suggest superior sample efficiency and systematic generalization for this framework in multi-modal reinforcement learning problems. Our code base is available here.

Ensuring safety via safety filters in real-world robotics presents significant challenges, particularly when the system dynamics is complex or unavailable. To handle this issue, learning-based safety filters recently gained popularity, which can be classified as model-based and model-free methods. Existing model-based approaches requires various assumptions on system model (e.g., control-affine), which limits their application in complex systems, and existing model-free approaches need substantial modifications to standard RL algorithms and lack versatility. This paper proposes a simple, plugin-and-play, and effective model-free safety filter learning framework. We introduce a novel reward formulation and use Q-learning to learn Q-value functions to safeguard arbitrary task specific nominal policies via filtering out their potentially unsafe actions. The threshold used in the filtering process is supported by our theoretical analysis. Due to its model-free nature and simplicity, our framework can be seamlessly integrated with various RL algorithms. We validate the proposed approach through simulations on double integrator and Dubin's car systems and demonstrate its effectiveness in real-world experiments with a soft robotic limb.

The Rubik's Cube, with its vast state space and sparse reward structure, presents a significant challenge for reinforcement learning (RL) due to the difficulty of reaching rewarded states. Previous research addressed this by propagating cost-to-go estimates from the solved state and incorporating search techniques. These approaches differ from human strategies that start from fully scrambled cubes, which can be tricky for solving a general sparse-reward problem. In this paper, we introduce a novel RL algorithm using policy gradient methods to solve the Rubik's Cube without relying on near solved-state sampling. Our approach employs a neural network to predict cost patterns between states, allowing the agent to learn directly from scrambled states. Our method was tested on the 2x2x2 Rubik's Cube, where the cube was scrambled 50,000 times, and the model successfully solved it in over 99.4% of cases. Notably, this result was achieved using only the policy network without relying on tree search as in previous methods, demonstrating its effectiveness and potential for broader applications in sparse-reward problems.

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact gradients, they can be unstable in contact-rich environments and may lead to poor generalization. This paper introduces a novel approach integrating sharpness-aware optimization into gradient-based reinforcement learning algorithms. Our simulation results demonstrate that our method, tested on contact-rich environments, significantly enhances policy robustness to environmental variations and action perturbations while maintaining the sample efficiency of first-order methods. Specifically, our approach improves action noise tolerance compared to standard first-order methods and achieves generalization comparable to zeroth-order methods. This improvement stems from finding flatter minima in the loss landscape, associated with better generalization. Our work offers a promising solution to balance efficient learning and robust sim-to-real transfer in robotics, potentially bridging the gap between simulation and real-world performance.