activity
20122019
most citedExploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning

31 citations · 78 across the 8 of their papers we have counts for

collaborators

8 papers

cs.LG201931 cited

Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning

Akanksha Atrey, Kaleigh Clary, David Jensen

Saliency maps are frequently used to support explanations of the behavior of deep reinforcement learning (RL) agents. However, a review of how saliency maps are used in practice in…

cs.AI201918 cited

The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data

Amanda Gentzel, Dan Garant, David Jensen

Causal inference is central to many areas of artificial intelligence, including complex reasoning, planning, knowledge-base construction, robotics, explanation, and fairness. An ac…

cs.AI20191 cited

Bayesian causal inference via probabilistic program synthesis

Sam Witty, Alexander Lew, David Jensen +1

Causal inference can be formalized as Bayesian inference that combines a prior distribution over causal models and likelihoods that account for both observations and interventions.…

cs.LG201916 cited

Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

Kaleigh Clary, Emma Tosch, John Foley +1

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itse…

cs.AI20195 cited

ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents

John Foley, Emma Tosch, Kaleigh Clary +1

It is a widely accepted principle that software without tests has bugs. Testing reinforcement learning agents is especially difficult because of the stochastic nature of both agent…

cs.AI20167 cited

Evaluating Causal Models by Comparing Interventional Distributions

Dan Garant, David Jensen

The predominant method for evaluating the quality of causal models is to measure the graphical accuracy of the learned model structure. We present an alternative method for evaluat…