Reinforcement Learning Posts

Self-Improving Robots: Embracing Autonomy in Robot Learning

Learning methods for robotics have a data problem. Autonomous robotic systems can deliver orders of magnitude more real-world embodied data than we have.

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Ajay Mandlekar

We conducted an extensive study of six offline learning algorithms for robot manipulation on five simulated and three real-world multi-stage manipulation tasks of varying complexity, and with datasets of varying quality. Our study analyzes the most critical challenges when learning from offline h...

iGibson: A Simulation Environment to Train AI Agents in Large Realistic Scenes

Roberto Martín-Martín

Introducing iGibson, an open source, fully academically developed simulation environment for interactive tasks in large realistic scenes.

Learning to Influence Multi-Agent Interaction

Annie Xie

We introduce a framework for multi-agent interaction that represents the low-level policies of non-stationary agents with high-level latent strategies.

GTI: Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations

Ajay Mandlekar, Danfei Xu

We developed Generalization Through Imitation (GTI) - an algorithm for learning visuomotor control from human demonstrations and generalizing to new long-horizon tasks by leveraging latent compositional structures.

Safety Validation of Black-Box Autonomous Systems

Anthony L. Corso

Validation of safety-critical autonomous systems is necessary before deployment and is made possible by black-box validation strategies. In this blog post, we provide a model for black-box safety validation and survey the literature to uncover the most effective validation techniques.

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning

Evan Zheran Liu

Adapting to new environments and tasks (e.g., cooking in a new kitchen) requires first gathering information via exploration (e.g., finding the ingredients). We identify a chicken-and-egg coupling problem that prevents existing approaches from effectively exploring, and we solve this with DREAM.

Making Sense of Vision and Touch: Multimodal Representations for Contact-Rich Tasks

Michelle A. Lee

Contact-rich manipulation tasks in unstructured environments often require both tactile and visual feedback. In this blog post, we introduce how to use self-supervision to learn a compact and multimodal representation of vision and touch.

Sequential Problem Solving by Hierarchical Planning in Latent Spaces

Kuan Fang

We propose a hierarchical planning algorithm in learned latent spaces. Our method uses deep generative models to prioritize promising actions for sampling-based planning.

RoboNet: A Dataset for Large-Scale Multi-Robot Learning

Sudeep Dasari

We introduce RoboNet, an open database for sharing robotic experience, and study how this data can be used to learn generalizable models for vision-based robotic manipulation. We find that pre-training on RoboNet enables faster learning in new environments compared to learning from scratch.