TractOracle: towards an anatomically-informed reward function for RL-based tractography

Reinforcement learning (RL)-based tractography is a competitive alternative to machine learning and classical tractography algorithms due to its high anatomical accuracy obtained without the need for any annotated data. However, the reward functions so far used to train RL agents do not encapsulate anatomical knowledge which causes agents to generate spurious false positives tracts. In this paper, we propose a new RL tractography system, TractOracle, which relies on a reward network trained for streamline classification. This network is used both as a reward function during training as well as a mean for stopping the tracking process early and thus reduce the number of false positive streamlines. This makes our system a unique method that evaluates and reconstructs WM streamlines at the same time. We report an improvement of true positive ratios by almost 20\% and a reduction of 3x of false positive ratios on one dataset and an increase between 2x and 7x in the number true positive streamlines on another dataset.

Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving

The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vital for obtaining robust and general policies. However, crafting traffic scenarios with multiple, heterogeneous agents is typically considered as a tedious and time-consuming task, especially in more complex simulation environments. In our work, we introduce MATS-Gym, a Multi-Agent Traffic Scenario framework to train agents in CARLA, a high-fidelity driving simulator. MATS-Gym is a multi-agent training framework for autonomous driving that uses partial scenario specifications to generate traffic scenarios with variable numbers of agents. This paper unifies various existing approaches to traffic scenario description into a single training framework and demonstrates how it can be integrated with techniques from unsupervised environment design to automate the generation of adaptive auto-curricula. The code is available at https://github.com/AutonomousDrivingExaminer/mats-gym.

Interpretable cancer cell detection with phonon microscopy using multi-task conditional neural networks for inter-batch calibration

Advances in artificial intelligence (AI) show great potential in revealing underlying information from phonon microscopy (high-frequency ultrasound) data to identify cancerous cells. However, this technology suffers from the 'batch effect' that comes from unavoidable technical variations between each experiment, creating confounding variables that the AI model may inadvertently learn. We therefore present a multi-task conditional neural network framework to simultaneously achieve inter-batch calibration, by removing confounding variables, and accurate cell classification of time-resolved phonon-derived signals. We validate our approach by training and validating on different experimental batches, achieving a balanced precision of 89.22% and an average cross-validated precision of 89.07% for classifying background, healthy and cancerous regions. Classification can be performed in 0.5 seconds with only simple prior batch information required for multiple batch corrections. Further, we extend our model to reconstruct denoised signals, enabling physical interpretation of salient features indicating disease state including sound velocity, sound attenuation and cell-adhesion to substrate.

BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat

Creating new air combat tactics and discovering novel maneuvers can require numerous hours of expert pilots' time. Additionally, for each different combat scenario, the same strategies may not work since small changes in equipment performance may drastically change the air combat outcome. For this reason, we created a reinforcement learning environment to help investigate potential air combat tactics in the field of beyond-visual-range (BVR) air combat: the BVR Gym. This type of air combat is important since long-range missiles are often the first weapon to be used in aerial combat. Some existing environments provide high-fidelity simulations but are either not open source or are not adapted to the BVR air combat domain. Other environments are open source but use less accurate simulation models. Our work provides a high-fidelity environment based on the open-source flight dynamics simulator JSBSim and is adapted to the BVR air combat domain. This article describes the building blocks of the environment and some use cases.

Chain of Compression: A Systematic Approach to Combinationally Compress Convolutional Neural Networks

Convolutional neural networks (CNNs) have achieved significant popularity, but their computational and memory intensity poses challenges for resource-constrained computing systems, particularly with the prerequisite of real-time performance. To release this burden, model compression has become an important research focus. Many approaches like quantization, pruning, early exit, and knowledge distillation have demonstrated the effect of reducing redundancy in neural networks. Upon closer examination, it becomes apparent that each approach capitalizes on its unique features to compress the neural network, and they can also exhibit complementary behavior when combined. To explore the interactions and reap the benefits from the complementary features, we propose the Chain of Compression, which works on the combinational sequence to apply these common techniques to compress the neural network. Validated on the image-based regression and classification networks across different data sets, our proposed Chain of Compression can significantly compress the computation cost by 100-1000 times with ignorable accuracy loss compared with the baseline model.

Destination-Constrained Linear Dynamical System Modeling in Set-Valued Frameworks

Directional motion towards a specified destination is a common occurrence in physical processes and human societal activities. Utilizing this prior information can significantly improve the control and predictive performance of system models. This paper primarily focuses on reconstructing linear dynamic system models based on destination constraints in the set-valued framework. We treat destination constraints as inherent information in the state evolution process and employ convex optimization techniques to construct a coherent and robust state model. This refined model effectively captures the impact of destination constraints on the state evolution at each time step. Furthermore, we design an optimal weight matrix for the reconstructed model to ensure smoother and more natural trajectories of state evolution. We also analyze the theoretical guarantee of optimality for this weight matrix and the properties of the reconstructed model. Finally, simulation experiments verify that the reconstructed model has significant advantages over the unconstrained and unoptimized weighted models and constrains the evolution of state trajectories with different starting and ending points.

Visual Whole-Body Control for Legged Loco-Manipulation

We study the problem of mobile manipulation using legged robots equipped with an arm, namely legged loco-manipulation. The robot legs, while usually utilized for mobility, offer an opportunity to amplify the manipulation capabilities by conducting whole-body control. That is, the robot can control the legs and the arm at the same time to extend its workspace. We propose a framework that can conduct the whole-body control autonomously with visual observations. Our approach, namely Visual Whole-Body Control(VBC), is composed of a low-level policy using all degrees of freedom to track the end-effector manipulator position and a high-level policy proposing the end-effector position based on visual inputs. We train both levels of policies in simulation and perform Sim2Real transfer for real robot deployment. We perform extensive experiments and show significant improvements over baselines in picking up diverse objects in different configurations (heights, locations, orientations) and environments. Project page: https://wholebody-b1.github.io

Path Integral Control with Rollout Clustering and Dynamic Obstacles

Model Predictive Path Integral (MPPI) control has proven to be a powerful tool for the control of uncertain systems (such as systems subject to disturbances and systems with unmodeled dynamics). One important limitation of the baseline MPPI algorithm is that it does not utilize simulated trajectories to their fullest extent. For one, it assumes that the average of all trajectories weighted by their performance index will be a safe trajectory. In this paper, multiple examples are shown where the previous assumption does not hold, and a trajectory clustering technique is presented that reduces the chances of the weighted average crossing in an unsafe region. Secondly, MPPI does not account for dynamic obstacles, so the authors put forward a novel cost function that accounts for dynamic obstacles without adding significant computation time to the overall algorithm. The novel contributions proposed in this paper were evaluated with extensive simulations to demonstrate improvements upon the state-of-the-art MPPI techniques.

Supervisory Prompt Training

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training (SPT). SPT automates the generation of highly effective prompts using a dual LLM system. In this system, one LLM, the generator, performs a task while the other, the corrector, provides feedback and generates improved prompts. In contrast to earlier techniques, both the generator and corrector collaboratively and continuously improve their prompts over time. We also introduce the concept of \textit{impact scores} to measure the sentence-level effectiveness of the prompts. Our method was tested on four benchmarks, testing the level of hallucinations in LLMs. Notably, we were able to increase the accuracy of GPT-4 on GSM8K from 65.8\% to 94.1\% (28.3\% increase). SPT advances LLMs by refining prompts to enhance performance and reduce hallucinations, offering an efficient and scalable alternative to traditional model fine-tuning.

Imitating Cost-Constrained Behaviors in Reinforcement Learning

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative to solving these problems. Generally speaking, imitation learning is designed to learn either the reward (or preference) model or directly the behavioral policy by observing the behavior of an expert. Existing work in imitation learning and inverse reinforcement learning has focused on imitation primarily in unconstrained settings (e.g., no limit on fuel consumed by the vehicle). However, in many real-world domains, the behavior of an expert is governed not only by reward (or preference) but also by constraints. For instance, decisions on self-driving delivery vehicles are dependent not only on the route preferences/rewards (depending on past demand data) but also on the fuel in the vehicle and the time available. In such problems, imitation learning is challenging as decisions are not only dictated by the reward model but are also dependent on a cost-constrained model. In this paper, we provide multiple methods that match expert distributions in the presence of trajectory cost constraints through (a) Lagrangian-based method; (b) Meta-gradients to find a good trade-off between expected return and minimizing constraint violation; and (c) Cost-violation-based alternating gradient. We empirically show that leading imitation learning approaches imitate cost-constrained behaviors poorly and our meta-gradient-based approach achieves the best performance.