Offline reinforcement learning (RL) methods strike a balance between
exp...
Training generally capable agents that perform well in unseen dynamic
en...
Learning from demonstrations (LfD) methods guide learning agents to a de...
We introduce Alexa Arena, a user-centric simulation platform for Embodie...
For service robots to become general-purpose in everyday household
envir...
Recent years have witnessed an emerging paradigm shift toward embodied
a...
Machine learning has long since become a keystone technology, accelerati...
We demonstrate the possibility of learning drone swarm controllers that ...
Language-guided robots performing home and office tasks must navigate in...
We explore possible methods for multi-task transfer learning which seek ...
Increasing the scale of reinforcement learning experiments has allowed
r...
Advances in optimization and constraint satisfaction techniques, togethe...
The recursive Newton-Euler Algorithm (RNEA) is a popular technique in
ro...
We present a meta-learning approach based on learning an adaptive,
high-...
We propose a hybrid approach aimed at improving the sample efficiency in...
A new mechanism for efficiently solving the Markov decision processes (M...
The solution convergence of Markov Decision Processes (MDPs) can be
acce...
Simulation-to-real transfer is an important strategy for making reinforc...
We present a novel solution to the problem of simulation-to-real transfe...
Learning a policy capable of moving an agent between any two states in t...
The problem of modeling and predicting spatiotemporal traffic phenomena ...