Pre-training robot policies with a rich set of skills can substantially
...
Reinforcement learning (RL), imitation learning (IL), and task and motio...
Program synthesis aims to automatically construct human-readable program...
Large-scale data is an essential component of machine learning as
demons...
Model-based reinforcement learning (RL) is a sample-efficient way of lea...
While deep reinforcement learning methods have shown impressive results ...
In this work, we evaluate the effectiveness of representation learning
a...
Skill chaining is a promising approach for synthesizing complex behavior...
Learning complex manipulation tasks in realistic, obstructed environment...
Recently, deep reinforcement learning (DRL) methods have achieved impres...
Demonstration-guided reinforcement learning (RL) is a promising approach...
The ability to transfer a policy from one environment to another is a
pr...
Intelligent agents rely heavily on prior experience when learning a new ...
Deep reinforcement learning (RL) agents are able to learn contact-rich
m...
Learning from demonstrations is a useful way to transfer a skill from on...
The IKEA Furniture Assembly Environment is one of the first benchmarks f...
Model-agnostic meta-learners aim to acquire meta-learned parameters from...
Gradient-based meta-learners such as MAML are able to learn a meta-prior...
Recent advancements in machine learning research have given rise to recu...
Understanding 3D object structure from a single image is an important bu...
We propose an unsupervised method for reference resolution in instructio...
Two less addressed issues of deep reinforcement learning are (1) lack of...