Return-Aligned Decision Transformer

The Return-Aligned Decision Transformer (RADT) is a novel decision-making model for offline reinforcement learning, proposed by researchers in a 2025 arXiv paper, designed to align an agent's actual return with a specified target return.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.