Offline reinforcement learning (RL) learns effective policies from a static target dataset. Despite state-of-the-art (SOTA) offline RL algorithms being promising, they highly rely on the quality of the target dataset. The performance of SOTA algorithms can degrade in scenarios with limited samples in the target dataset, which is often the case in real-world applications. To address this issue, domain adaptation that leverages auxiliary samples from related source datasets (such as simulators) can be beneficial. In this context, determining the optimal way to trade off the source and target datasets remains a critical challenge in offline RL. To the best of our knowledge, this paper proposes the first framework that theoretically and experimentally explores how the weight assigned to each dataset affects the performance of offline RL. We establish the performance bounds and convergence neighborhood of our framework, both of which depend on the selection of the weight. Furthermore, we identify the existence of an optimal weight for balancing the two datasets. All theoretical guarantees and optimal weight depend on the quality of the source dataset and the size of the target dataset. Our empirical results on the well-known Procgen Benchmark substantiate our theoretical contributions.

Procedural Content Generation via Reinforcement Learning (PCGRL) has been introduced as a means by which controllable designer agents can be trained based only on a set of computable metrics acting as a proxy for the level's quality and key characteristics. While PCGRL offers a unique set of affordances for game designers, it is constrained by the compute-intensive process of training RL agents, and has so far been limited to generating relatively small levels. To address this issue of scale, we implement several PCGRL environments in Jax so that all aspects of learning and simulation happen in parallel on the GPU, resulting in faster environment simulation; removing the CPU-GPU transfer of information bottleneck during RL training; and ultimately resulting in significantly improved training speed. We replicate several key results from prior works in this new framework, letting models train for much longer than previously studied, and evaluating their behavior after 1 billion timesteps. Aiming for greater control for human designers, we introduce randomized level sizes and frozen "pinpoints" of pivotal game tiles as further ways of countering overfitting. To test the generalization ability of learned generators, we evaluate models on large, out-of-distribution map sizes, and find that partial observation sizes learn more robust design strategies.

Preference-based reinforcement learning (PbRL) stands out by utilizing human preferences as a direct reward signal, eliminating the need for intricate reward engineering. However, despite its potential, traditional PbRL methods are often constrained by the indivisibility of annotations, which impedes the learning process. In this paper, we introduce a groundbreaking approach, Skill-Enhanced Preference Optimization Algorithm~(S-EPOA), which addresses the annotation indivisibility issue by integrating skill mechanisms into the preference learning framework. Specifically, we first conduct the unsupervised pretraining to learn useful skills. Then, we propose a novel query selection mechanism to balance the information gain and discriminability over the learned skill space. Experimental results on a range of tasks, including robotic manipulation and locomotion, demonstrate that S-EPOA significantly outperforms conventional PbRL methods in terms of both robustness and learning efficiency. The results highlight the effectiveness of skill-driven learning in overcoming the challenges posed by annotation indivisibility.

Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for large datasets. In contrast, unlabelled data tends to be less expensive. This situation highlights the importance of finding effective ways to use unlabelled data in offline RL, especially when labelled data is limited or expensive to obtain. In this paper, we present the algorithm to utilize the unlabeled data in the offline RL method with kernel function approximation and give the theoretical guarantee. We present various eigenvalue decay conditions of $\mathcal{H}_k$ which determine the complexity of the algorithm. In summary, our work provides a promising approach for exploiting the advantages offered by unlabeled data in offline RL, whilst maintaining theoretical assurances.

Utilizing deep learning models to learn part-based representations holds significant potential for interpretable-by-design approaches, as these models incorporate latent causes obtained from feature representations through simple addition. However, training a part-based learning model presents challenges, particularly in enforcing non-negative constraints on the model's parameters, which can result in training difficulties such as instability and convergence issues. Moreover, applying such approaches in Deep Reinforcement Learning (RL) is even more demanding due to the inherent instabilities that impact many optimization methods. In this paper, we propose a non-negative training approach for actor models in RL, enabling the extraction of part-based representations that enhance interpretability while adhering to non-negative constraints. To this end, we employ a non-negative initialization technique, as well as a modified sign-preserving training method, which can ensure better gradient flow compared to existing approaches. We demonstrate the effectiveness of the proposed approach using the well-known Cartpole benchmark.

High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-consuming endeavor. Existing approaches for learning or optimizing these parameters often require numerous real-world executions or do not work in dynamic environments. To address these challenges, we propose MuTT, a novel encoder-decoder transformer architecture designed to predict environment-aware executions of robot skills by integrating vision, trajectory, and robot skill parameters. Notably, we pioneer the fusion of vision and trajectory, introducing a novel trajectory projection. Furthermore, we illustrate MuTT's efficacy as a predictor when combined with a model-based robot skill optimizer. This approach facilitates the optimization of robot skill parameters for the current environment, without the need for real-world executions during optimization. Designed for compatibility with any representation of robot skills, MuTT demonstrates its versatility across three comprehensive experiments, showcasing superior performance across two different skill representations.

Osteoarthritis (OA) is the most common musculoskeletal disease, which has no cure. Knee OA (KOA) is one of the highest causes of disability worldwide, and it costs billions of United States dollars to the global community. Prediction of KOA progression has been of high interest to the community for years, as it can advance treatment development through more efficient clinical trials and improve patient outcomes through more efficient healthcare utilization. Existing approaches for predicting KOA, however, are predominantly static, i.e. consider data from a single time point to predict progression many years into the future, and knee level, i.e. consider progression in a single joint only. Due to these and related reasons, these methods fail to deliver the level of predictive performance, which is sufficient to result in cost savings and better patient outcomes. Collecting extensive data from all patients on a regular basis could address the issue, but it is limited by the high cost at a population level. In this work, we propose to go beyond static prediction models in OA, and bring a novel Active Sensing (AS) approach, designed to dynamically follow up patients with the objective of maximizing the number of informative data acquisitions, while minimizing their total cost over a period of time. Our approach is based on Reinforcement Learning (RL), and it leverages a novel reward function designed specifically for AS of disease progression in more than one part of a human body. Our method is end-to-end, relies on multi-modal Deep Learning, and requires no human input at inference time. Throughout an exhaustive experimental evaluation, we show that using RL can provide a higher monetary benefit when compared to state-of-the-art baselines.

Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using human-preference alignment techniques, such as best-of-n sampling and reinforcement learning. However, these techniques face the difficulty arising from the scarcity of visual preference data, which is required to train a visual reward model (VRM). In this work, we continue the line of research. We present a Robust Visual Reward Model (RoVRM) which improves human-preference alignment for LVLMs. RoVRM leverages auxiliary textual preference data through a three-phase progressive training and optimal transport-based preference data selection to effectively mitigate the scarcity of visual preference data. We experiment with RoVRM on the commonly used vision-language tasks based on the LLaVA-1.5-7B and -13B models. Experimental results demonstrate that RoVRM consistently outperforms traditional VRMs. Furthermore, our three-phase progressive training and preference data selection approaches can yield consistent performance gains over ranking-based alignment techniques, such as direct preference optimization.

Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the challenges of exploration and dimensionality explosion. Hierarchical reinforcement learning (HRL) offers a structured approach to decompose complex tasks into simpler sub-tasks, which is promising for multi-agent settings. This paper advances the field by introducing a hierarchical architecture that autonomously generates effective subgoals without explicit constraints, enhancing both flexibility and stability in training. We propose a dynamic goal generation strategy that adapts based on environmental changes. This method significantly improves the adaptability and sample efficiency of the learning process. Furthermore, we address the critical issue of credit assignment in multi-agent systems by synergizing our hierarchical architecture with a modified QMIX network, thus improving overall strategy coordination and efficiency. Comparative experiments with mainstream reinforcement learning algorithms demonstrate the superior convergence speed and performance of our approach in both single-agent and multi-agent environments, confirming its effectiveness and flexibility in complex scenarios. Our code is open-sourced at: \url{https://github.com/SICC-Group/GMAH}.

The superiority of Multi-Robot Systems (MRS) in various complex environments is unquestionable. However, in complex situations such as search and rescue, environmental monitoring, and automated production, robots are often required to work collaboratively without a central control unit. This necessitates an efficient and robust decentralized control mechanism to process local information and guide the robots' behavior. In this work, we propose a new decentralized controller design method that utilizes the Deep Q-Network (DQN) algorithm from deep reinforcement learning, aimed at improving the integration of local information and robustness of multi-robot systems. The designed controller allows each robot to make decisions independently based on its local observations while enhancing the overall system's collaborative efficiency and adaptability to dynamic environments through a shared learning mechanism. Through testing in simulated environments, we have demonstrated the effectiveness of this controller in improving task execution efficiency, strengthening system fault tolerance, and enhancing adaptability to the environment. Furthermore, we explored the impact of DQN parameter tuning on system performance, providing insights for further optimization of the controller design. Our research not only showcases the potential application of the DQN algorithm in the decentralized control of multi-robot systems but also offers a new perspective on how to enhance the overall performance and robustness of the system through the integration of local information.