Related papers: Imagination Policy: Using Generative Point Cloud M…

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed…

Standard model-free reinforcement learning algorithms optimize a policy that generates the action to be taken in the current time step in order to maximize expected future return. While flexible, it faces difficulties arising from the…

Many machine learning systems are built to solve the hardest examples of a particular task, which often makes them large and expensive to run---especially with respect to the easier examples, which might require much less computation. For…

Learning a disentangled representation of the latent space has become one of the most fundamental problems studied in computer vision. Recently, many Generative Adversarial Networks (GANs) have shown promising results in generating high…

The paper presents a complete pipeline for learning continuous motion control policies for a mobile robot when only a non-differentiable physics simulator of robot-terrain interactions is available. The multi-modal state estimation of the…

Learning from demonstrations has gained increasing interest in the recent past, enabling an agent to learn how to make decisions by observing an experienced teacher. While many approaches have been proposed to solve this problem, there is…

In order to solve complex, long-horizon tasks, intelligent robots need to carry out high-level, abstract planning and reasoning in conjunction with motion planning. However, abstract models are typically lossy and plans or policies computed…

Large Language Models (LLMs) have been successful at generating robot policy code, but so far these results have been limited to high-level tasks that do not require precise movement. It is an open question how well such approaches work for…

Autonomous learning of object manipulation skills can enable robots to acquire rich behavioral repertoires that scale to the variety of objects found in the real world. However, current motion skill learning methods typically restrict the…

Simulation offers a promising approach for cheaply scaling training data for generalist policies. To scalably generate data from diverse and realistic tasks, existing algorithms either rely on large language models (LLMs) that may…

Although point cloud models have gained significant improvements in prediction accuracy over recent years, their trustworthiness is still not sufficiently investigated. In terms of global explainability, Activation Maximization (AM)…

In robotic manipulation tasks, achieving a designated target state for the manipulated object is often essential to facilitate motion planning for robotic arms. Specifically, in tasks such as hanging a mug, the mug must be positioned within…

Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The…

Recent video generation models demonstrate remarkable ability to capture complex physical interactions and scene evolution over time. To leverage their spatiotemporal priors, robotics works have adapted video models for policy learning but…

We introduce a new framework that performs decision-making in reinforcement learning (RL) as an iterative reasoning process. We model agent behavior as the steady-state distribution of a parameterized reasoning Markov chain (RMC), optimized…

Representation and generative learning, as reconstruction-based methods, have demonstrated their potential for mutual reinforcement across various domains. In the field of point cloud processing, although existing studies have adopted…

Neural networks are often regarded as universal equations that can estimate any function. This flexibility, however, comes with the drawback of high complexity, rendering these networks into black box models, which is especially relevant in…

The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-level planning from demonstrations has proven challenging,…

Bimanual manipulation requires policies that can reason about 3D geometry, anticipate how it evolves under action, and generate smooth, coordinated motions. However, existing methods typically rely on 2D features with limited spatial…

Generative models can be used to synthesize 3D objects of high quality and diversity. However, there is typically no control over the properties of the generated object.This paper proposes a novel generative adversarial network (GAN) setup…