Ajay U. Mandlekar – Research
Recent News
[July 2020] We are organizing the Advances and Challenges in Imitation Learning for Robotics workshop at RSS 2020.
[July 2020] Our new algorithm, Generalization Through Imitation (GTI), will appear at RSS 2020. It enables learning visuomotor control from human demonstrations and generalizing to new long-horizon tasks by leveraging latent compositional structures. See our paper, website, and video for more details.
[May 2020] Our paper on offline learning from large-scale robot manipulation datasets appeared at ICRA 2020. We demonstrated that our algorithm can learn from our crowdsourced RoboTurk dataset without requiring additional interaction. See our paper, website, and talk for more details!
Publications
 |
Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations |
 |
IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data |
 |
Controlling Assistive Robots with Learned Latent Actions |
 |
Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity
|
 |
AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers |
 |
RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation |
 |
Adversarially Robust Policy Learning: Active Construction of Physically-Plausible Perturbations |
 |
Risk-sensitive Inverse Reinforcement Learning via Coherent Risk Models |