DeepAI AI Chat
Log In Sign Up

Measuring Interventional Robustness in Reinforcement Learning

by   Katherine Avery, et al.

Recent work in reinforcement learning has focused on several characteristics of learned policies that go beyond maximizing reward. These properties include fairness, explainability, generalization, and robustness. In this paper, we define interventional robustness (IR), a measure of how much variability is introduced into learned policies by incidental aspects of the training procedure, such as the order of training data or the particular exploratory actions taken by agents. A training procedure has high IR when the agents it produces take very similar actions under intervention, despite variation in these incidental aspects of the training procedure. We develop an intuitive, quantitative measure of IR and calculate it for eight algorithms in three Atari environments across dozens of interventions and states. From these experiments, we find that IR varies with the amount of training and type of algorithm and that high performance does not imply high IR, as one might expect.


page 4

page 7

page 12

page 13

page 14

page 15


Does QRAT simulate IR-calc? QRAT simulation algorithm for ∀Exp+Res cannot be lifted to IR-calc

We show that the QRAT simulation algorithm of ∀Exp+Res from [B. Kiesl an...

Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks

This effort is focused on examining the behavior of reinforcement learni...

Safer Reinforcement Learning through Transferable Instinct Networks

Random exploration is one of the main mechanisms through which reinforce...

TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents

Recent work has identified that classification models implemented as neu...

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

We present the first framework of Certifying Robust Policies for reinfor...

Reinforcement Learning Your Way: Agent Characterization through Policy Regularization

The increased complexity of state-of-the-art reinforcement learning (RL)...

Let's measure run time! Extending the IR replicability infrastructure to include performance aspects

Establishing a docker-based replicability infrastructure offers the comm...