Picture for Aaron M. Roth

Aaron M. Roth

MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation

Add code
Sep 19, 2022
Figure 1 for MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation
Figure 2 for MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation
Figure 3 for MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation
Figure 4 for MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation
Viaarxiv icon

XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees

Add code
Apr 22, 2021
Figure 1 for XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees
Figure 2 for XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees
Figure 3 for XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees
Figure 4 for XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees
Viaarxiv icon

A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game

Add code
Oct 24, 2019
Figure 1 for A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game
Figure 2 for A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game
Figure 3 for A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game
Figure 4 for A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game
Viaarxiv icon

Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy

Add code
Jul 02, 2019
Figure 1 for Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
Figure 2 for Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
Figure 3 for Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
Figure 4 for Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
Viaarxiv icon

The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting

Add code
Jun 10, 2018
Figure 1 for The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting
Figure 2 for The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting
Viaarxiv icon