We thank the reviewers for their comments. However, Section 2.4 of the supplement demonstrates that a single model trained on all three shape categories still gives How does CaSPR generalize to unseen categories? Yet, this is a formidable open problem in computer vision and ML beyond the scope of our work. CaSPR, we focus on many other problems of importance by leveraging a category-level prior on object shape. Prior spatiotemporal (Occupancy Flow) and point cloud reconstruction (PointFlow) methods lack this step.

We study a class of optimization problems motivated by automating the design and update of AI systems like coding assistants, robots, and copilots. AutoDiff frameworks, like PyTorch, enable efficient end-to-end optimization of differentiable systems. However, general computational workflows can be non-differentiable and involve rich feedback (e.g.

This paper introduces the risk-sensitive control as inference (RCaI) that extends CaI by using Rényi divergence variational inference. RCaI is shown to be equivalent to log-probability regularized risk-sensitive control, which is an extension of the maximum entropy (MaxEnt) control. We also prove that the risk-sensitive optimal policy can be obtained by solving a soft Bellman equation, which reveals several equivalences between RCaI, MaxEnt control, the optimal posterior for CaI, and linearly-solvable control. Moreover, based on RCaI, we derive the risk-sensitive reinforcement learning (RL) methods: the policy gradient and the soft actor-critic. As the risk-sensitivity parameter vanishes, we recover the risk-neutral CaI and RL, which means that RCaI is a unifying framework. Furthermore, we give another risksensitive generalization of the MaxEnt control using Rényi entropy regularization. We show that in both of our extensions, the optimal policies have the same structure even though the derivations are very different.

We introduce the framework of performative control, where the policy chosen by the controller affects the underlying dynamics of the control system.

We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is tasked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical results demonstrate the benefits of using the learned representation from the upstream offline task instead of directly learning the representation of the low-rank model.

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically sparse and loose without consideration of geometric consistency, which makes the subsequent fine matching rely on ineffective optimal transport and hypothesis-andselection methods for consistency. Therefore, these methods are neither efficient nor scalable for real-time applications such as odometry in robotics. To address these issues, we design a consistency-aware spot-guided Transformer (CAST), which incorporates a spot-guided cross-attention module to avoid interfering with irrelevant areas, and a consistency-aware self-attention module to enhance matching capabilities with geometrically consistent correspondences. Furthermore, a lightweight fine matching module for both sparse keypoints and dense features can estimate the transformation accurately. Extensive experiments on both outdoor LiDAR point cloud datasets and indoor RGBD point cloud datasets demonstrate that our method achieves state-of-the-art accuracy, efficiency, and robustness. Our code is available at https://github.com/RenlangHuang/CAST.

SAVE 150: As of May 30, the iRobot Roomba Q0120 is on sale for 99.99 at Amazon. If you've been shopping around for a robot vacuum for a while, the name Roomba won't be unfamiliar. And as of May 30, it is currently on sale for 99.99, saving you 150. Despite being a lower price than many you'll have seen elsewhere, this doesn't mean a lack of quality; you're still getting a top-of-the-range vacuuming experience. This model has a three-stage cleaning system that delivers customizable suction for carpets and hard floors. It comes with smart navigation that vacuums in neat rows, dodges furniture, and steers clear of stairs or any other obstacles in your house.

We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment. The world model tries to explain its interactions, while also being optimistic about what reward it can achieve. We define this optimism as a logical constraint between a program and a planner. We study our agent on gridworlds, and on task planning, finding our approach is more sample-efficient compared to deep RL, more compute-efficient compared to ReAct-style agents, and that it can transfer its knowledge across environments by editing its code.

Claire chatted to Nick Thompson from BOW about software that makes robots easier to program. Nick Thompson is CEO of BOW and exited founder of One Beyond Ltd, an international software development firm. His career started in 1997 as a software engineer, founded One Beyond in the early 2000's and after 20 years in the business sold to a private equity firm. In 2022 he was recognised as one of the UK's'Most Ambitious Business Leaders' by LDC Private Equity Group.

We thank all reviewers for their constructive comments. Due to space limit, we address the major concerns as follows. This is the main reason why we have to prepare our own synthetic data. We will improve the description of GPNet-Naive in the paper. Our grasp parametrization using surface contact, grasp center, and'pitch' angle Fig.1), where we prune grasp proposals by antipodal We will include these results in the paper.