11 accepted papers
While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable conv…
Given access to accurate dynamical models, modern planning approaches are effective in computing feasible and optimal plans for repetitive robotic tasks. However, it is difficult to model the true dynamics of the real world before execution, especially for tasks requiring interactions with objects w…
We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching. At its core, our classification scheme is based on whether the learner attempts to match (1) reward or (2) action-value moments of the expert’s behavior, with each option leadi…
In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near- optimal cost-to-go oracle on the planning horizon and demonstrate that the cost- to-go oracle shortens the learner’s planning horizon as f…
How can a robot design a sequence of grasping actions that will succeed despite the presence of bounded state uncertainty and an inherently stochastic system? In this letter, we propose a probabilistic algorithm that generates sequential actions to iteratively reduce uncertainty until object pose is
Recently, researchers have demonstrated state-of-the-art performance on sequential prediction problems using deep neural networks and Reinforcement Learning (RL). For some of these problems, oracles that can demonstrate good performance may be available during training, but are not used by plain RL…
We propose a polynomial force-motion model for planar sliding. The set of generalized friction loads is the 1-sublevel set of a polynomial whose gradient directions correspond to generalized velocities. Additionally, the polynomial is confined to be convex even-degree homogeneous in order to obey th…
As robots aspire for long-term autonomous operations in complex dynamic environments, the ability to reliably take mission-critical decisions in ambiguous situations becomes critical. This motivates the need to build systems that have situational awareness to assess how quali ed they are at that mom…
We formalize the problem of adapting a demonstrated trajectory to a new start and goal configuration as an optimization problem over a Hilbert space of trajectories: minimize the distance between the demonstration and the new trajectory subject to the new end point constraints. We show that the comm…
We present a simple approach for producing a small number of structured visual outputs which have high recall, for a variety of tasks including monocular pose estimation and semantic scene segmentation. Current state-of-the-art approaches learn a single model and modify inference procedures to produ…
We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons about the locations of multiple object instances in an image while expressively describing object boundaries. We design…