Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Scott Niekum

Scott Niekum

Ranking-Based Reward Extrapolation without Rankings

Jul 09, 2019
Daniel S. Brown, Wonjoon Goo, Scott Niekum

Figure 1 for Ranking-Based Reward Extrapolation without Rankings

Figure 2 for Ranking-Based Reward Extrapolation without Rankings

Figure 3 for Ranking-Based Reward Extrapolation without Rankings

Figure 4 for Ranking-Based Reward Extrapolation without Rankings

Access Paper or Ask Questions

A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms

Jul 06, 2019
Oliver Kroemer, Scott Niekum, George Konidaris

Figure 1 for A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms

Figure 2 for A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms

Access Paper or Ask Questions

Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

May 27, 2019
Caleb Chuck, Supawit Chockchowwat, Scott Niekum

Figure 1 for Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Figure 2 for Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Figure 3 for Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Figure 4 for Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

* Submitted to NeurIPS 2019

Access Paper or Ask Questions

Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

May 14, 2019
Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan, Scott Niekum

Figure 1 for Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

Figure 2 for Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

Figure 3 for Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

Figure 4 for Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

* In proceedings of Thirty-sixth International Conference on Machine Learning (ICML 2019)

Access Paper or Ask Questions

Uncertainty-Aware Data Aggregation for Deep Imitation Learning

May 07, 2019
Yuchen Cui, David Isele, Scott Niekum, Kikuo Fujimura

Figure 1 for Uncertainty-Aware Data Aggregation for Deep Imitation Learning

Figure 2 for Uncertainty-Aware Data Aggregation for Deep Imitation Learning

Figure 3 for Uncertainty-Aware Data Aggregation for Deep Imitation Learning

Figure 4 for Uncertainty-Aware Data Aggregation for Deep Imitation Learning

* Accepted to International Conference on Robotics and Automation 2019

Access Paper or Ask Questions

Using Natural Language for Reward Shaping in Reinforcement Learning

Mar 05, 2019
Prasoon Goyal, Scott Niekum, Raymond J. Mooney

Figure 1 for Using Natural Language for Reward Shaping in Reinforcement Learning

Figure 2 for Using Natural Language for Reward Shaping in Reinforcement Learning

Figure 3 for Using Natural Language for Reward Shaping in Reinforcement Learning

Figure 4 for Using Natural Language for Reward Shaping in Reinforcement Learning

Access Paper or Ask Questions

Risk-Aware Active Inverse Reinforcement Learning

Jan 08, 2019
Daniel S. Brown, Yuchen Cui, Scott Niekum

Figure 1 for Risk-Aware Active Inverse Reinforcement Learning

Figure 2 for Risk-Aware Active Inverse Reinforcement Learning

Figure 3 for Risk-Aware Active Inverse Reinforcement Learning

Figure 4 for Risk-Aware Active Inverse Reinforcement Learning

* In proceedings of Conference on Robot Learning (CoRL) 2018

Access Paper or Ask Questions

LAAIR: A Layered Architecture for Autonomous Interactive Robots

Nov 09, 2018
Yuqian Jiang, Nick Walker, Minkyu Kim, Nicolas Brissonneau, Daniel S. Brown, Justin W. Hart, Scott Niekum, Luis Sentis, Peter Stone

Figure 1 for LAAIR: A Layered Architecture for Autonomous Interactive Robots

Figure 2 for LAAIR: A Layered Architecture for Autonomous Interactive Robots

Figure 3 for LAAIR: A Layered Architecture for Autonomous Interactive Robots

* Presented at LTA AAAI-FSS, 2018

Access Paper or Ask Questions

Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics

Oct 08, 2018
Ajinkya Jain, Scott Niekum

Figure 1 for Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics

Figure 2 for Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics

Figure 3 for Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics

* 2nd Conference on Robot Learning (CoRL 2018), Zurich, Switzerland

Access Paper or Ask Questions