Decision Transformer: Reinforcement Learning via Sequence Modeling

by UC Berkeley / Google Brain · free · Last verified 2026-03-17

Decision Transformer recasts offline reinforcement learning as a conditional sequence modeling problem, predicting actions given return-to-go, states, and past actions using a causal Transformer. This eliminates the need for temporal difference learning and bootstrapping while achieving competitive performance on Atari and MuJoCo benchmarks.