Safety-Constrained Policy Transfer with Successor Features
Transfer source policies to a target reinforcement learning task with safety constraints using Successor Features.
Collaborative Learning and Adaptive Robots (CLeAR) Lab.
Below, you’ll find our contributions to robot/machine learning. Much of our work is on learning from (or interacting with) humans. However, you'll also find some works that are purely curiosity-driven. For example, at CLeAR, we have developed new deep generative models that are based on gradient flows and structured temporal models that can capture complex relationships, yet are interpretable and useful for planning and decision-making. We believe this works are crucial for finding "out-of-the-box" ideas and novel techniques for developing robot skills.
Transfer source policies to a target reinforcement learning task with safety constraints using Successor Features.
This paper proposes SCALES, a general framework that translates well-established fairness principles into a common representation based on CMDPs.
We develop an accurate physics-inspired model for describing how a population of Q-learning agents adapt as they interact.
Inspired by Social Projection Theory, we use the robot's self model to efficiently model humans.
We propose a deep switching state space model that can capture both state-dependent and time-dependent switching patterns in time series data.
We embed symbolic knowledge expressed as linear temporal logic (LTL) and use these embeddings to guide the training of deep sequential models.
We construct a shared latent space from different sensory modalities via contrastive learning.
Bridging the gap between symbolic and connectionist paradigms via Graph Neural Network embeddings
Using Gradient Flows to Refine Samples from Deep Generative Models
Training robots that can interactively assist humans with private information
Leveraging prior symbolic knowledge to improve the performance of deep models.
Using Bayesian Optimization to address the ill-posed nature of Inverse Reinforcement Learning