Simon Stepputtis

Characterizing Out-of-Distribution Error via Optimal Transport

May 25, 2023
Yuzhe Lu, Yilong Qin, Runtian Zhai, Andrew Shen, Ketong Chen, Zhenlin Wang, Soheil Kolouri, Simon Stepputtis, Joseph Campbell, Katia Sycara

Access Paper or Ask Questions

Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Feb 23, 2023
Renos Zabounidis, Joseph Campbell, Simon Stepputtis, Dana Hughes, Katia Sycara

Figure 2 for Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Figure 3 for Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Figure 4 for Concept Learning for Interpretable Multi-Agent Reinforcement Learning

* Accepted to the 6th Conference on Robot Learning (CoRL 2022), Auckland, New Zealand

Access Paper or Ask Questions

Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation

Dec 08, 2022
Yifan Zhou, Shubham Sonawani, Mariano Phielipp, Simon Stepputtis, Heni Ben Amor

Figure 2 for Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation

Figure 3 for Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation

Figure 4 for Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation

* 2022 Conference on Robot Learning (CoRL)

Access Paper or Ask Questions

Explainable Action Advising for Multi-Agent Reinforcement Learning

Nov 15, 2022
Yue Guo, Joseph Campbell, Simon Stepputtis, Ruiyu Li, Dana Hughes, Fei Fang, Katia Sycara

Figure 2 for Explainable Action Advising for Multi-Agent Reinforcement Learning

Figure 3 for Explainable Action Advising for Multi-Agent Reinforcement Learning

Figure 4 for Explainable Action Advising for Multi-Agent Reinforcement Learning

Access Paper or Ask Questions

A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies

Aug 01, 2022
Simon Stepputtis, Maryam Bandari, Stefan Schaal, Heni Ben Amor

Figure 2 for A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies

Figure 3 for A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies

Figure 4 for A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies

* Accepted to the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan

Access Paper or Ask Questions

Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Oct 22, 2020
Simon Stepputtis, Joseph Campbell, Mariano Phielipp, Stefan Lee, Chitta Baral, Heni Ben Amor

Figure 2 for Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Figure 3 for Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Figure 4 for Language-Conditioned Imitation Learning for Robot Manipulation Tasks

* Accepted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada as spotlight presentation

Access Paper or Ask Questions

Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration

Nov 26, 2019
Simon Stepputtis, Joseph Campbell, Mariano Phielipp, Chitta Baral, Heni Ben Amor

Figure 2 for Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration

* Accepted to the NeurIPS 2019 Workshop on Robot Learning: Control and Interaction in the Real World, Vancouver, Canada

Access Paper or Ask Questions

Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

Nov 15, 2019
Kevin Sebastian Luck, Mel Vecerik, Simon Stepputtis, Heni Ben Amor, Jonathan Scholz

Figure 2 for Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

Figure 3 for Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

Figure 4 for Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

* Accepted for IROS 2019

Access Paper or Ask Questions

Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives

Aug 15, 2019
Joseph Campbell, Arne Hitzmann, Simon Stepputtis, Shuhei Ikemoto, Koh Hosoda, Heni Ben Amor

Figure 2 for Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives

Figure 3 for Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives

Figure 4 for Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives

* Accompanying video: https://youtu.be/2fxOn3lIdvo

Access Paper or Ask Questions

Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks

Aug 14, 2019
Joseph Campbell, Simon Stepputtis, Heni Ben Amor

Figure 2 for Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks

Figure 3 for Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks

Figure 4 for Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks

* Project website: http://interactive-robotics.engineering.asu.edu/interaction-primitives Accompanying video: https://youtu.be/r5AqfxTDfLA

Access Paper or Ask Questions