7 accepted papers
Many applications in Reinforcement Learning (RL) usually have noise or stochasticity present in the environment. Beyond their impact on learning, these uncertainties lead the exact same policy to perform differently, i.e. yield different return, from one roll-out to another. Common evaluation proced…
Data-driven learning based methods have recently been particularly successful at learning robust locomotion controllers for a variety of unstructured terrains. Prior work has shown that incorporating good locomotion priors in the form of trajectory generators (TGs) is effective at efficiently learni…
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were trained on, and thus do not perform well when conditions devia…
Quality-Diversity (QD) algorithms are powerful exploration algorithms that allow robots to discover large repertoires of diverse and high-performing skills. However, QD algorithms are sample inefficient and require millions of evaluations. In this paper, we propose Dynamics-Aware Quality-Diversity (…
Animal-level agility and robustness in robots cannot be accomplished by solely relying on blind locomotion controllers. A significant portion of a robot’s ability to traverse terrain comes from reacting to the external world through visual sensing. However, embedding the sensors and compute that pro…
In this paper, we present an approach to tactile pose estimation from the first touch for known objects. First, we create an object-agnostic map from real tactile observations to contact shapes. Next, for a new object with known geometry, we learn a tailored perception model completely in simulation
Electronic health records provide a rich source of data for machine learning methods to learn dynamic treatment responses over time. However, any direct estimation is hampered by the presence of time-dependent confounding, where actions taken are dependent on time-varying variables related to the ou…