Our new framework provides various measures of RL agent competence stemming from interestingness analysis and is applicable to a wide range of RL algorithms.
A Framework for understanding and Visualizing Strategies of RL Agents
We present a framework for learning comprehensible models of sequential decision tasks in which agent strategies are characterized using temporal logic formulas.
Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space
We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior.
Confidence Calibration for Domain Generalization under Covariate Shift
We present novel calibration solutions via domain generalization. Our core idea is to leverage multiple calibration domains to reduce the effective distribution disparity between the target and calibration domains for improved calibration transfer without needing any data from the target domain.
Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents’ Capabilities and Limitations
We propose an explainable reinforcement learning (XRL) framework that analyzes an agent’s history of interaction with the environment to extract interestingness elements that explain its behavior.
Learning Procedures by Augmenting Sequential Pattern Mining with Planning Knowledge
This paper explores the use of filtering heuristics based on action models for automated planning to augment sequence mining techniques.
Bridging the Gap: Converting Human Advice into Imagined Examples
We present an approach that converts human advice into synthetic or imagined training experiences, serving to scaffold the low-level representations of simple, reactive learning systems such as reinforcement learners.
Interestingness Elements for Explainable Reinforcement Learning through Introspection
The framework uses introspective analysis of an agent’s history of interaction with its environment to extract several interestingness elements regarding its behavior.
Explanation to Avert Surprise
We present an explanation framework based on the notion of explanation drivers —i.e., the intent or purpose behind agent explanations. We focus on explanations meant to reconcile expectation violations and enumerate a set of triggers for proactive explanation.