Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …

The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …

Humans can perform parkour by traversing obstacles in a highly dynamic fashion requiring
precise eye-muscle coordination and movement. Getting robots to do the same task requires …

Animals are capable of precise and agile locomotion using vision. Replicating this ability
has been a long-standing goal in robotics. The traditional approach has been to decompose …

Simulation-based reinforcement learning approaches are leading the next innovations in
legged robot control. However, the resulting control policies are still not applicable on soft …

Deep reinforcement learning is a promising approach to learning policies in uncontrolled
environments that do not require domain knowledge. Unfortunately, due to sample …