Reinforcement Learning (RL) has emerged as a powerful tool for neural combinatorial optimization, enabling models to learn heuristics that solve complex problems without requiring expert knowledge. Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast combinatorial action spaces, leading to inefficiency. In this paper, we propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling, emphasizing the superiority among sampled solutions. Methodologically, by reparameterizing the reward function in terms of policy and utilizing preference models, we formulate an entropy-regularized RL objective that aligns the policy directly with preferences while avoiding intractable computations. Furthermore, we integrate local search techniques into the fine-tuning rather than post-processing to generate high-quality preference pairs, helping the policy escape local optima. Empirical results on various benchmarks, such as the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP) and the Flexible Flow Shop Problem (FFSP), demonstrate that our method significantly outperforms existing RL algorithms, achieving superior convergence efficiency and solution quality.

-- Unmanned Aerial V ehicle (UA V) Coverage Path Planning (CPP) is critical for applications such as precision agriculture and search and rescue. While traditional methods rely on discrete grid-based representations, real-world UA V operations require power-efficient continuous motion planning. We formulate the UA V CPP problem in a continuous environment, minimizing power consumption while ensuring complete coverage. We train a reinforcement learning agent using an action-mapping-based Soft Actor-Critic (AM-SAC) algorithm employing a self-adaptive curriculum. Experiments on both procedurally generated and hand-crafted scenarios demonstrate the effectiveness of our method in learning energy-efficient coverage strategies. Unmanned Aerial V ehicle (UA V) Coverage Path Planning (CPP) is a challenging problem with numerous real-world applications.

We present an iterative inverse reinforcement learning algorithm to infer optimal cost functions in continuous spaces. Based on a popular maximum entropy criteria, our approach iteratively finds a weight improvement step and proposes a method to find an appropriate step size that ensures learned cost function features remain similar to the demonstrated trajectory features. In contrast to similar approaches, our algorithm can individually tune the effectiveness of each observation for the partition function and does not need a large sample set, enabling faster learning. We generate sample trajectories by solving an optimal control problem instead of random sampling, leading to more informative trajectories. The performance of our method is compared to two state of the art algorithms to demonstrate its benefits in several simulated environments.

In disaster scenarios, establishing robust emergency communication networks is critical, and unmanned aerial vehicles (UAVs) offer a promising solution to rapidly restore connectivity. However, organizing UAVs to form multi-hop networks in large-scale dynamic environments presents significant challenges, including limitations in algorithmic scalability and the vast exploration space required for coordinated decision-making. To address these issues, we propose MRLMN, a novel framework that integrates multi-agent reinforcement learning (MARL) and large language models (LLMs) to jointly optimize UAV agents toward achieving optimal networking performance. The framework incorporates a grouping strategy with reward decomposition to enhance algorithmic scalability and balance decision-making across UAVs. In addition, behavioral constraints are applied to selected key UAVs to improve the robustness of the network. Furthermore, the framework integrates LLM agents, leveraging knowledge distillation to transfer their high-level decision-making capabilities to MARL agents. This enhances both the efficiency of exploration and the overall training process. In the distillation module, a Hungarian algorithm-based matching scheme is applied to align the decision outputs of the LLM and MARL agents and define the distillation loss. Extensive simulation results validate the effectiveness of our approach, demonstrating significant improvements in network performance, including enhanced coverage and communication quality.

Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous control tasks. However, there is currently limited research on how to optimize diffusion-based polices (e.g., Diffusion Policy) fast and stably. In this paper, we propose an Adam-based Diffusion Policy Optimization (ADPO), a fast algorithmic framework containing best practices for fine-tuning diffusion-based polices in robotic control tasks using the adaptive gradient descent method in RL. Adaptive gradient method is less studied in training RL, let alone diffusion-based policies. We confirm that ADPO outperforms other diffusion-based RL methods in terms of overall effectiveness for fine-tuning on standard robotic tasks. Concretely, we conduct extensive experiments on standard robotic control tasks to test ADPO, where, particularly, six popular diffusion-based RL methods are provided as benchmark methods. Experimental results show that ADPO acquires better or comparable performance than the baseline methods. Finally, we systematically analyze the sensitivity of multiple hyperparameters in standard robotics tasks, providing guidance for subsequent practical applications. Our video demonstrations are released in https://github.com/Timeless-lab/ADPO.git.

Vision-language models (VLMs) have demonstrated excellent high-level planning capabilities, enabling locomotion skill learning from video demonstrations without the need for meticulous human-level reward design. However, the improper frame sampling method and low training efficiency of current methods remain a critical bottleneck, resulting in substantial computational overhead and time costs. To address this limitation, we propose Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos (MA-ROESL). MA-ROESL integrates a motion-aware frame selection method to implicitly enhance the quality of VLM-generated reward functions. It further employs a hybrid three-phase training pipeline that improves training efficiency via rapid reward optimization and derives the final policy through online fine-tuning. Experimental results demonstrate that MA-ROESL significantly enhances training efficiency while faithfully reproducing locomotion skills in both simulated and real-world settings, thereby underscoring its potential as a robust and scalable framework for efficient robot locomotion skill learning from video demonstrations.

Generalization in reinforcement learning (RL) remains a significant challenge, especially when agents encounter novel environments with unseen dynamics. Drawing inspiration from human compositional reasoning--where known components are reconfigured to handle new situations--we introduce World Modeling with Compositional Causal Components (WM3C). This novel framework enhances RL generalization by learning and leveraging compositional causal components. Unlike previous approaches focusing on invariant representation learning or meta-learning, WM3C identifies and utilizes causal dynamics among composable elements, facilitating robust adaptation to new tasks. Our approach integrates language as a compositional modality to decompose the latent space into meaningful components and provides theoretical guarantees for their unique identification under mild assumptions. Our practical implementation uses a masked autoencoder with mutual information constraints and adaptive sparsity regularization to capture high-level semantic information and effectively disentangle transition dynamics. Experiments on numerical simulations and real-world robotic manipulation tasks demonstrate that WM3C significantly outperforms existing methods in identifying latent processes, improving policy learning, and generalizing to unseen tasks. Reinforcement learning (RL) has rapidly progressed, driving innovations in domains such as game playing, robotics, and autonomous driving (Silver et al., 2018; Vinyals et al., 2019; Shi et al., 2022; Kiran et al., 2020). Deep reinforcement learning (DRL) methods, including Deep Q-Networks (DQN), Soft Actor-Critic (SAC), and Proximal Policy Optimization (PPO), have addressed various challenges in RL, such as stability in training, exploration in large state spaces, and efficient policy optimization (Haarnoja et al., 2018; Schulman et al., 2017; Mnih et al., 2015; 2016; Fuji-moto et al., 2018). These breakthroughs underscore the pivotal role of DRL in advancing artificial intelligence. Despite these substantial advancements, one of the most pressing issues of DRL is the generalization of learned policies to novel, unseen environments (Gamrian & Goldberg, 2018; Song et al., 2019; Cobbe et al., 2018). For example, the policy excels in push ball to place A might perform notoriously poorly in the task push ball to place B .

Multirotors play a significant role in diverse field robotics applications but remain highly susceptible to actuator failures, leading to rapid instability and compromised mission reliability. While various fault-tolerant control (FTC) strategies using reinforcement learning (RL) have been widely explored, most previous approaches require prior knowledge of the multirotor model or struggle to adapt to new configurations. To address these limitations, we propose a novel hybrid RL-based FTC framework integrated with a transformer-based online adaptation module. Our framework leverages a transformer architecture to infer latent representations in real time, enabling adaptation to previously unseen system models without retraining. We evaluate our method in a PyBullet simulation under loss-of-effectiveness actuator faults, achieving a 95% success rate and a positional root mean square error (RMSE) of 0.129 m, outperforming existing adaptation methods with 86% success and an RMSE of 0.153 m. Further evaluations on quadrotors with varying configurations confirm the robustness of our framework across untrained dynamics. These results demonstrate the potential of our framework to enhance the adaptability and reliability of multirotors, enabling efficient fault management in dynamic and uncertain environments. Website is available at http://00dhkim.me/paper/rl-ftc

The ability to learn from large batches of autonomously collected data for policy improvement -- a paradigm we refer to as batch online reinforcement learning -- holds the promise of enabling truly scalable robot learning by significantly reducing the need for human effort of data collection while getting benefits from self-improvement. Yet, despite the promise of this paradigm, it remains challenging to achieve due to algorithms not being able to learn effectively from the autonomous data. For example, prior works have applied imitation learning and filtered imitation learning methods to the batch online RL problem, but these algorithms often fail to efficiently improve from the autonomously collected data or converge quickly to a suboptimal point. This raises the question of what matters for effective batch online RL in robotics. Motivated by this question, we perform a systematic empirical study of three axes -- (i) algorithm class, (ii) policy extraction methods, and (iii) policy expressivity -- and analyze how these axes affect performance and scaling with the amount of autonomous data. Through our analysis, we make several observations. First, we observe that the use of Q-functions to guide batch online RL significantly improves performance over imitation-based methods. Building on this, we show that an implicit method of policy extraction -- via choosing the best action in the distribution of the policy -- is necessary over traditional policy extraction methods from offline RL. Next, we show that an expressive policy class is preferred over less expressive policy classes. Based on this analysis, we propose a general recipe for effective batch online RL. We then show a simple addition to the recipe of using temporally-correlated noise to obtain more diversity results in further performance gains. Our recipe obtains significantly better performance and scaling compared to prior methods.

Recent studies claim that human behavior in a two-armed Bernoulli bandit (TABB) task is described by positivity and confirmation biases, implying that humans do not integrate new information objectively. However, we find that even if the agent updates its belief via objective Bayesian inference, fitting the standard Q-learning model with asymmetric learning rates still recovers both biases. Bayesian inference cast as an effective Q-learning algorithm has symmetric, though decreasing, learning rates. We explain this by analyzing the stochastic dynamics of these learning systems using master equations. We find that both confirmation bias and unbiased but decreasing learning rates yield the same behavioral signatures. Finally, we propose experimental protocols to disentangle true cognitive biases from artifacts of decreasing learning rates.