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

Add to Chrome

Add to Firefox

Picture for Charles Isbell

Charles Isbell

Hard Attention Control By Mutual Information Maximization

Mar 10, 2021
Himanshu Sahni, Charles Isbell

Figure 1 for Hard Attention Control By Mutual Information Maximization

Figure 2 for Hard Attention Control By Mutual Information Maximization

Figure 3 for Hard Attention Control By Mutual Information Maximization

Figure 4 for Hard Attention Control By Mutual Information Maximization

Access Paper or Ask Questions

A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play

Jun 10, 2020
Shray Bansal, Jin Xu, Ayanna Howard, Charles Isbell

Figure 1 for A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play

Figure 2 for A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play

Figure 3 for A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play

Figure 4 for A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play

* Accepted at Robotics: Science and Systems (RSS) 2020

Access Paper or Ask Questions

Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning

Feb 15, 2020
Yannick Schroecker, Charles Isbell

Figure 1 for Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning

Figure 2 for Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning

Figure 3 for Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning

Figure 4 for Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning

Access Paper or Ask Questions

Learning to Compose Skills

Nov 30, 2017
Himanshu Sahni, Saurabh Kumar, Farhan Tejani, Charles Isbell

Figure 1 for Learning to Compose Skills

Figure 2 for Learning to Compose Skills

Figure 3 for Learning to Compose Skills

Figure 4 for Learning to Compose Skills

* Presented at NIPS 2017 Deep RL Symposium

Access Paper or Ask Questions

State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning

May 24, 2017
Himanshu Sahni, Saurabh Kumar, Farhan Tejani, Yannick Schroecker, Charles Isbell

Figure 1 for State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning

Figure 2 for State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning

* 5 pages, 6 figures; 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2017), Ann Arbor, Michigan

Access Paper or Ask Questions

Perceptual Reward Functions

Aug 12, 2016
Ashley Edwards, Charles Isbell, Atsuo Takanishi

Figure 1 for Perceptual Reward Functions

Figure 2 for Perceptual Reward Functions

Figure 3 for Perceptual Reward Functions

Figure 4 for Perceptual Reward Functions

* Deep Reinforcement Learning: Frontiers and Challenges Workshop, IJCAI 2016

Access Paper or Ask Questions