Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
For offline reinforcement learning practitioners, SlimDT offers a more efficient alternative to Decision Transformer with improved performance, though the improvement is incremental over existing methods.
SlimDT removes Return-to-Go (RTG) tokens from the autoregressive sequence in Decision Transformer, injecting RTG information into state representations instead. This reduces sequence length by one-third, improving inference efficiency while surpassing standard DT on D4RL benchmarks and matching state-of-the-art methods.
Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return-to-Go (RTG), state, and action tokens. However, RTG is a scalar that summarizes future rewards, containing far less information than typical state or action vectors, yet it consumes the same computational budget per token. Worse, the self-attention cost of Transformers grows quadratically with sequence length, so including RTG as a separate token adds unnecessary overhead. We propose SlimDT, which removes RTG from the autoregressive sequence. Instead, we inject RTG information into the state representations before the sequential modeling step, allowing the Transformer to process only a compact (state, action) sequence. This reduces the sequence length by one-third, directly improving inference efficiency. On the D4RL benchmark, SlimDT surpasses standard DT across various tasks and achieves performance comparable to existing state-of-the-art methods. Decoupling a sparse conditioning signal from an information-rich sequence thus yields both computational gains and higher task performance.