Search Results for author:
Found 18 papers, 10 papers with code
On-Robot Reinforcement Learning with Goal-Contrastive Rewards
We find that GCR leads to a more-sample efficient RL, enabling model-free RL to solve about twice as many tasks as our baseline reward learning methods.
Equivariant Offline Reinforcement Learning
Sample efficiency is critical when applying learning-based methods to robotic manipulation due to the high cost of collecting expert demonstrations and the challenges of on-robot policy learning through online Reinforcement Learning (RL).
Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies
Humans can imagine goal states during planning and perform actions to match those goals.
Equivariant Single View Pose Prediction Via Induced and Restricted Representations
We show that an algorithm that learns a three-dimensional representation of the world from two dimensional images must satisfy certain geometric consistency properties which we formulate as SO(2)-equivariance constraints.
One-shot Imitation Learning via Interaction Warping
We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration.
On Robot Grasp Learning Using Equivariant Models
Real-world grasp detection is challenging due to the stochasticity in grasp dynamics and the noise in hardware.
Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
Predicting the pose of objects from a single image is an important but difficult computer vision problem.
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning.
Image to Icosahedral Projection for $\mathrm{SO}(3)$ Object Reasoning from Single-View Images
In this paper, we propose a novel architecture based on icosahedral group convolutions that reasons in $\mathrm{SO(3)}$ by learning a projection of the input image onto an icosahedron.
Binding Actions to Objects in World Models
We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms.
Learning Symmetric Embeddings for Equivariant World Models
Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations.
Factored World Models for Zero-Shot Generalization in Robotic Manipulation
In this paper, we learn to generalize over robotic pick-and-place tasks using object-factored world models, which combat the combinatorial explosion by ensuring that predictions are equivariant to permutations of objects.
Learning Symmetric Representations for Equivariant World Models
In this paper, we use equivariant transition models as an inductive bias to learn symmetric latent representations in a self-supervised manner.
Equivariant Grasp learning In Real Time
Visual grasp detection is a key problem in robotics where the agent must learn to model the grasp function, a mapping from an image of a scene onto a set of feasible grasp poses.
The Impact of Negative Sampling on Contrastive Structured World Models
World models trained by contrastive learning are a compelling alternative to autoencoder-based world models, which learn by reconstructing pixel states.
Action Priors for Large Action Spaces in Robotics
This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks.
Learning Discrete State Abstractions With Deep Variational Inference
In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstraction.
Online Abstraction with MDP Homomorphisms for Deep Learning
Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy.
