Generalization across environments is critical to the successful application of reinforcement
learning (RL) algorithms to real-world challenges. In this work we propose a method for …

We propose a vision-proprioception model for planar object pushing, efficiently integrating
all necessary information from the environment. A Variational Autoencoder (VAE) is used to …

Policies for partially observed Markov decision processes can be efficiently learned by
imitating expert policies generated using asymmetric information. Unfortunately, existing …

Model-based RL is a promising approach for real-world robotics due to its improved sample
efficiency and generalization capabilities compared to model-free RL. However, effective …

We present a novel approach to address the challenge of generalization in offline
reinforcement learning (RL), where the agent learns from a fixed dataset without any …

In recent years, data-driven learning methods have been widely studied for autonomous
robot skill learning. However, these methods rely on large amounts of robot–environment …

Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by
the growth of required resources, expansive datasets and corresponding investments into …

There is a clear desire to model and comprehend human behavior. Trends in research
covering this topic show a clear assumption that many view human reasoning as the …

Using privileged information during training can improve the sample efficiency and
performance of machine learning systems. This paradigm has been applied to reinforcement …

We need to look at our shoelaces as we first learn to tie them but having mastered this skill,
can do it from touch alone. We call this phenomenon" sensory scaffolding": observation …