Facility location problems on graphs are ubiquitous in real world and hold significant importance, yet their resolution is often impeded by NP-hardness. Recently, machine learning methods have been proposed to tackle such classical problems, but they are limited to the myopic constructive pattern and only consider the problems in Euclidean space. To overcome these limitations, we propose a general swap-based framework that addresses the p-median problem and the facility relocation problem on graphs and a novel reinforcement learning model demonstrating a keen awareness of complex graph structures. Striking a harmonious balance between solution quality and running time, our method surpasses handcrafted heuristics on intricate graph datasets. Additionally, we introduce a graph generation process to simulate real-world urban road networks with demand, facilitating the construction of large datasets for the classic problem. For the initialization of the locations of facilities, we introduce a physics-inspired strategy for the p-median problem, reaching more stable solutions than the random strategy. The proposed pipeline coupling the classic swap-based method with deep reinforcement learning marks a significant step forward in addressing the practical challenges associated with facility location on graphs.

The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants, there's a growing expectation for them to perform consistently across various domains. However, previous work shows that Reinforcement Learning (RL) often exploits shortcuts to attain high rewards and overlooks challenging samples. This focus on quick reward gains undermines both the stability in training and the model's ability to generalize to new, unseen data. In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains. Given the challenges associated with acquiring group annotations, our method automatically classifies data into different groups, deliberately maximizing performance variance. Then, we optimize the policy to perform well on challenging groups. Lastly, leveraging the established groups, our approach adaptively adjusts the exploration space, allocating more learning capacity to more challenging data and preventing the model from over-optimizing on simpler data. Experimental results indicate that our approach significantly enhances training stability and model generalization.

Many optimal control problems require the simultaneous output of continuous and discrete control variables. Such problems are usually formulated as mixed-integer optimal control (MIOC) problems, which are challenging to solve due to the complexity of the solution space. Numerical methods such as branch-and-bound are computationally expensive and unsuitable for real-time control. This brief proposes a novel continuous-discrete reinforcement learning (CDRL) algorithm, twin delayed deep deterministic actor-Q (TD3AQ), for MIOC problems. TD3AQ combines the advantages of both actor-critic and Q-learning methods, and can handle the continuous and discrete action spaces simultaneously. The proposed algorithm is evaluated on a plug-in hybrid electric vehicle (PHEV) energy management problem, where real-time control of the continuous variable, engine torque, and discrete variables, gear shift and clutch engagement/disengagement is essential to maximize fuel economy while satisfying driving constraints. Simulation results on different drive cycles show that TD3AQ achieves near-optimal control compared to dynamic programming (DP) and outperforms baseline reinforcement learning algorithms.

This work focuses on the problem of visual target navigation, which is very important for autonomous robots as it is closely related to high-level tasks. To find a special object in unknown environments, classical and learning-based approaches are fundamental components of navigation that have been investigated thoroughly in the past. However, due to the difficulty in the representation of complicated scenes and the learning of the navigation policy, previous methods are still not adequate, especially for large unknown scenes. Hence, we propose a novel framework for visual target navigation using the frontier semantic policy. In this proposed framework, the semantic map and the frontier map are built from the current observation of the environment. Using the features of the maps and object category, deep reinforcement learning enables to learn a frontier semantic policy which can be used to select a frontier cell as a long-term goal to explore the environment efficiently. Experiments on Gibson and Habitat-Matterport 3D (HM3D) demonstrate that the proposed framework significantly outperforms existing map-based methods in terms of success rate and efficiency. Ablation analysis also indicates that the proposed approach learns a more efficient exploration policy based on the frontiers. A demonstration is provided to verify the applicability of applying our model to real-world transfer. The supplementary video and code can be accessed via the following link: https://sites.google.com/view/fsevn.

Traditional visual servoing methods suffer from serving between scenes from multiple perspectives, which humans can complete with visual signals alone. In this paper, we investigated how multi-perspective visual servoing could be solved under robot-specific constraints, including self-collision, singularity problems. We presented a novel learning-based multi-perspective visual servoing framework, which iteratively estimates robot actions from latent space representations of visual states using reinforcement learning. Furthermore, our approaches were trained and validated in a Gazebo simulation environment with connection to OpenAI/Gym. Through simulation experiments, we showed that our method can successfully learn an optimal control policy given initial images from different perspectives, and it outperformed the Direct Visual Servoing algorithm with mean success rate of 97.0%.

Previous soft tissue manipulation studies assumed that the grasping point was known and the target deformation can be achieved. During the operation, the constraints are supposed to be constant, and there is no obstacles around the soft tissue. To go beyond these assumptions, a deep reinforcement learning framework with prior knowledge is proposed for soft tissue manipulation under unknown constraints, such as the force applied by fascia. The prior knowledge is represented through an intuitive manipulation strategy. As an action of the agent, a regulator factor is used to coordinate the intuitive approach and the deliberate network. A reward function is designed to balance the exploration and exploitation for large deformation. Successful simulation results verify that the proposed framework can manipulate the soft tissue while avoiding obstacles and adding new position constraints. Compared with the soft actor-critic (SAC) algorithm, the proposed framework can accelerate the training procedure and improve the generalization.

We propose a novel model-based offline Reinforcement Learning (RL) framework, called Adversarial Model for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon an arbitrary reference policy regardless of data coverage. ARMOR is designed to optimize policies for the worst-case performance relative to the reference policy through adversarially training a Markov decision process model. In theory, we prove that ARMOR, with a well-tuned hyperparameter, can compete with the best policy within data coverage when the reference policy is supported by the data. At the same time, ARMOR is robust to hyperparameter choices: the policy learned by ARMOR, with "any" admissible hyperparameter, would never degrade the performance of the reference policy, even when the reference policy is not covered by the dataset. To validate these properties in practice, we design a scalable implementation of ARMOR, which by adversarial training, can optimize policies without using model ensembles in contrast to typical model-based methods. We show that ARMOR achieves competent performance with both state-of-the-art offline model-free and model-based RL algorithms and can robustly improve the reference policy over various hyperparameter choices.

The challenges inherent to long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To alleviate these challenges, we introduce a novel algorithm, Variational Autoencoder-based Subgoal Inference (VAESI), to accomplish long-horizon tasks through a divide-and-conquer manner. VAESI consists of three components: a Variational Autoencoder (VAE)-based Subgoal Generator, a Hindsight Sampler, and a Value Selector. The VAE-based Subgoal Generator draws inspiration from the human capacity to infer subgoals and reason about the final goal in the context of these subgoals. It is composed of an explicit encoder model, engineered to generate subgoals, and an implicit decoder model, designed to enhance the quality of the generated subgoals by predicting the final goal. Additionally, the Hindsight Sampler selects valid subgoals from an offline dataset to enhance the feasibility of the generated subgoals. The Value Selector utilizes the value function in reinforcement learning to filter the optimal subgoals from subgoal candidates. To validate our method, we conduct several long-horizon tasks in both simulation and the real world, including one locomotion task and three manipulation tasks. The obtained quantitative and qualitative data indicate that our approach achieves promising performance compared to other baseline methods. These experimental results can be seen in the website \url{https://sites.google.com/view/vaesi/home}.

Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-agent utilities. To ensure Individual-Global-Maximum property, existing works often focus on value factorization using monotonic functions, which are known to result in restricted representation expressiveness. In this paper, we analyze the limitations of monotonic factorization and present ConcaveQ, a novel non-monotonic value function factorization approach that goes beyond monotonic mixing functions and employs neural network representations of concave mixing functions. Leveraging the concave property in factorization, an iterative action selection scheme is developed to obtain optimal joint actions during training. It is used to update agents' local policy networks, enabling fully decentralized execution. The effectiveness of the proposed ConcaveQ is validated across scenarios involving multi-agent predator-prey environment and StarCraft II micromanagement tasks. Empirical results exhibit significant improvement of ConcaveQ over state-of-the-art multi-agent reinforcement learning approaches.

Problem definition: Supply chains are constantly evolving networks. Reinforcement learning is increasingly proposed as a solution to provide optimal control of these networks. Academic/practical: However, learning in continuously varying environments remains a challenge in the reinforcement learning literature. Methodology: This paper therefore seeks to address whether agents can control varying supply chain problems, transferring learning between environments that require different strategies and avoiding catastrophic forgetting of tasks that have not been seen in a while. To evaluate this approach, two state-of-the-art Reinforcement Learning (RL) algorithms are compared: an actor-critic learner, Proximal Policy Optimisation (PPO), and a Recurrent Proximal Policy Optimisation (RPPO), PPO with a Long Short-Term Memory (LSTM) layer, which is showing popularity in online learning environments. Results: First these methods are compared on six sets of environments with varying degrees of stochasticity. The results show that more lean strategies adopted in Batch environments are different from those adopted in Stochastic environments with varying products. The methods are also compared on various continuous supply chain scenarios, where the PPO agents are shown to be able to adapt through continuous learning when the tasks are similar but show more volatile performance when changing between the extreme tasks. However, the RPPO, with an ability to remember histories, is able to overcome this to some extent and takes on a more realistic strategy. Managerial implications: Our results provide a new perspective on the continuously varying supply chain, the cooperation and coordination of agents are crucial for improving the overall performance in uncertain and semi-continuous non-stationary supply chain environments without the need to retrain the environment as the demand changes.