Picture for Andrew Patterson

Andrew Patterson

When is Offline Policy Selection Sample Efficient for Reinforcement Learning?

Add code
Dec 04, 2023
Viaarxiv icon

Empirical Design in Reinforcement Learning

Add code
Apr 03, 2023
Figure 1 for Empirical Design in Reinforcement Learning
Figure 2 for Empirical Design in Reinforcement Learning
Figure 3 for Empirical Design in Reinforcement Learning
Figure 4 for Empirical Design in Reinforcement Learning
Viaarxiv icon

Robust Losses for Learning Value Functions

May 17, 2022
Figure 1 for Robust Losses for Learning Value Functions
Figure 2 for Robust Losses for Learning Value Functions
Figure 3 for Robust Losses for Learning Value Functions
Figure 4 for Robust Losses for Learning Value Functions
Viaarxiv icon

A Temporal-Difference Approach to Policy Gradient Estimation

Add code
Feb 04, 2022
Figure 1 for A Temporal-Difference Approach to Policy Gradient Estimation
Figure 2 for A Temporal-Difference Approach to Policy Gradient Estimation
Figure 3 for A Temporal-Difference Approach to Policy Gradient Estimation
Figure 4 for A Temporal-Difference Approach to Policy Gradient Estimation
Viaarxiv icon

A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning

Add code
Apr 28, 2021
Figure 1 for A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
Figure 2 for A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
Figure 3 for A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
Figure 4 for A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
Viaarxiv icon

$\mathcal{RL}_1$-$\mathcal{GP}$: Safe Simultaneous Learning and Control

Sep 08, 2020
Figure 1 for $\mathcal{RL}_1$-$\mathcal{GP}$: Safe Simultaneous Learning and Control
Figure 2 for $\mathcal{RL}_1$-$\mathcal{GP}$: Safe Simultaneous Learning and Control
Figure 3 for $\mathcal{RL}_1$-$\mathcal{GP}$: Safe Simultaneous Learning and Control
Figure 4 for $\mathcal{RL}_1$-$\mathcal{GP}$: Safe Simultaneous Learning and Control
Viaarxiv icon

Gradient Temporal-Difference Learning with Regularized Corrections

Add code
Jul 07, 2020
Figure 1 for Gradient Temporal-Difference Learning with Regularized Corrections
Figure 2 for Gradient Temporal-Difference Learning with Regularized Corrections
Figure 3 for Gradient Temporal-Difference Learning with Regularized Corrections
Figure 4 for Gradient Temporal-Difference Learning with Regularized Corrections
Viaarxiv icon

Learning Probabilistic Intersection Traffic Models for Trajectory Prediction

Feb 05, 2020
Figure 1 for Learning Probabilistic Intersection Traffic Models for Trajectory Prediction
Figure 2 for Learning Probabilistic Intersection Traffic Models for Trajectory Prediction
Figure 3 for Learning Probabilistic Intersection Traffic Models for Trajectory Prediction
Figure 4 for Learning Probabilistic Intersection Traffic Models for Trajectory Prediction
Viaarxiv icon

Proximity Queries for Absolutely Continuous Parametric Curves

Add code
Apr 09, 2019
Figure 1 for Proximity Queries for Absolutely Continuous Parametric Curves
Figure 2 for Proximity Queries for Absolutely Continuous Parametric Curves
Figure 3 for Proximity Queries for Absolutely Continuous Parametric Curves
Figure 4 for Proximity Queries for Absolutely Continuous Parametric Curves
Viaarxiv icon

Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification

Apr 04, 2019
Figure 1 for Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification
Figure 2 for Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification
Figure 3 for Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification
Figure 4 for Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification
Viaarxiv icon