Picture for Richard Lewis

Richard Lewis

GrASP: Gradient-Based Affordance Selection for Planning

Add code
Feb 08, 2022
Figure 1 for GrASP: Gradient-Based Affordance Selection for Planning
Figure 2 for GrASP: Gradient-Based Affordance Selection for Planning
Figure 3 for GrASP: Gradient-Based Affordance Selection for Planning
Figure 4 for GrASP: Gradient-Based Affordance Selection for Planning
Viaarxiv icon

Pairwise Weights for Temporal Credit Assignment

Add code
Feb 09, 2021
Figure 1 for Pairwise Weights for Temporal Credit Assignment
Figure 2 for Pairwise Weights for Temporal Credit Assignment
Figure 3 for Pairwise Weights for Temporal Credit Assignment
Figure 4 for Pairwise Weights for Temporal Credit Assignment
Viaarxiv icon

Learning State Representations from Random Deep Action-conditional Predictions

Add code
Feb 09, 2021
Figure 1 for Learning State Representations from Random Deep Action-conditional Predictions
Figure 2 for Learning State Representations from Random Deep Action-conditional Predictions
Figure 3 for Learning State Representations from Random Deep Action-conditional Predictions
Figure 4 for Learning State Representations from Random Deep Action-conditional Predictions
Viaarxiv icon

How Should an Agent Practice?

Add code
Dec 15, 2019
Figure 1 for How Should an Agent Practice?
Figure 2 for How Should an Agent Practice?
Figure 3 for How Should an Agent Practice?
Figure 4 for How Should an Agent Practice?
Viaarxiv icon

Discovery of Useful Questions as Auxiliary Tasks

Add code
Sep 10, 2019
Figure 1 for Discovery of Useful Questions as Auxiliary Tasks
Figure 2 for Discovery of Useful Questions as Auxiliary Tasks
Figure 3 for Discovery of Useful Questions as Auxiliary Tasks
Figure 4 for Discovery of Useful Questions as Auxiliary Tasks
Viaarxiv icon

In silico generation of novel, drug-like chemical matter using the LSTM neural network

Add code
Jan 08, 2018
Figure 1 for In silico generation of novel, drug-like chemical matter using the LSTM neural network
Figure 2 for In silico generation of novel, drug-like chemical matter using the LSTM neural network
Figure 3 for In silico generation of novel, drug-like chemical matter using the LSTM neural network
Figure 4 for In silico generation of novel, drug-like chemical matter using the LSTM neural network
Viaarxiv icon

Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games

Add code
Apr 24, 2016
Figure 1 for Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games
Figure 2 for Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games
Figure 3 for Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games
Figure 4 for Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games
Viaarxiv icon

Action-Conditional Video Prediction using Deep Networks in Atari Games

Add code
Dec 22, 2015
Figure 1 for Action-Conditional Video Prediction using Deep Networks in Atari Games
Figure 2 for Action-Conditional Video Prediction using Deep Networks in Atari Games
Figure 3 for Action-Conditional Video Prediction using Deep Networks in Atari Games
Figure 4 for Action-Conditional Video Prediction using Deep Networks in Atari Games
Viaarxiv icon