1

Symmetry-Aware Actor-Critic for 3D Molecular Design

We propose an actor-critic architecture for 3D molecular design that exploits the symmetries of the design process using spherical harmonics.

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

We present a reinforcement learning formulation that enables molecular design directly in Cartesian coordinates.

Bayesian Batch Active Learning as Sparse Subset Approximation

We propose a novel Bayesian batch active learning approach motivated by approximating the complete data posterior of the model parameters.

Factored Contextual Policy Search with Bayesian Optimization

We factor contexts for contextual policy search into environment and target components, such that experience can be directly generalized over target contexts.

Sample and feedback efficient hierarchical reinforcement learning from human preferences

We incorporate bi-perspective reward learning from human preferences into a general hierarchical reinforcement learning framework for robotic grasping.