Finding Useful Predictions by Meta-gradient Descent to Improve Decision-making

Kearney, Alex; Koop, Anna; Günther, Johannes; Pilarski, Patrick M.

doi:10.48550/arxiv.2111.11212

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Forecasts can be made and learned in an entirely self-supervised fashion: agents do not require labeled examples nor a human ontology to form abstract relationships. This enables agents to construct new abstract relationships from its own stream of experience by adding new predictions over time (Sherstan et al, 2018b;Veeriah et al, 2019;Kearney et al, 2021) without human prompting or input.…”

Section: Predictions: the Foundation Of Agent Perceptionmentioning

confidence: 99%

“…Prior to rationalizing a decision to external agents and human designers, an agent must commit to a decision itself-an agent must choose an action a t using the information available to itself o t . In predictive knowledge systems, GVF forecasts are often a key component of this observation o t (Edwards et al, 2016b;Günther, 2018;Kearney et al, 2021;Ring, 2021;Schlegel et al, 2021). However, not all predictions are created equally.…”

Section: Introspective Explanationmentioning

confidence: 99%

See 1 more Smart Citation

Prediction, Knowledge, and Explainability: Examining the Use of General Value Functions in Machine Knowledge

Kearney¹,

Günther²,

Pilarski³

2022

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

Within computational reinforcement learning, a growing body of work seeks to express an agent's knowledge of its world through large collections of predictions. While systems that encode predictions as General Value Functions (GVFs) have seen numerous developments in both theory and application, whether such approaches are explainable is unexplored. In this perspective piece, we explore GVFs as a form of explainable AI. To do so, we articulate a subjective agent-centric approach to explainability in sequential decision-making tasks. We propose that prior to explaining its decisions to others, an self-supervised agent must be able to introspectively explain decisions to itself. To clarify this point, we review prior applications of GVFs that involve human-agent collaboration. In doing so, we demonstrate that by making their subjective explanations public, predictive knowledge agents can improve the clarity of their operation in collaborative tasks.

show abstract

Section: Predictions: the Foundation Of Agent Perceptionmentioning

confidence: 99%