Skill Decision Transformer

TL;DR

The paper introduces Skill Decision Transformer, a method that discovers diverse primitive behaviors from offline data using reward-free optimization, improving behavior diversity and performance in offline RL tasks.

Contribution

It presents Skill Decision Transformer, a novel approach combining hindsight relabelling and skill discovery for diverse behavior extraction in offline RL.

Findings

Skill DT can perform offline state-marginal matching.

It discovers descriptive, easily sampleable skills.

It remains competitive with supervised offline RL methods.

Abstract

Recent work has shown that Large Language Models (LLMs) can be incredibly effective for offline reinforcement learning (RL) by representing the traditional RL problem as a sequence modelling problem (Chen et al., 2021; Janner et al., 2021). However many of these methods only optimize for high returns, and may not extract much information from a diverse dataset of trajectories. Generalized Decision Transformers (GDTs) (Furuta et al., 2021) have shown that utilizing future trajectory information, in the form of information statistics, can help extract more information from offline trajectory data. Building upon this, we propose Skill Decision Transformer (Skill DT). Skill DT draws inspiration from hindsight relabelling (Andrychowicz et al., 2017) and skill discovery methods to discover a diverse set of primitive behaviors, or skills. We show that Skill DT can not only perform offline state-marginal matching (SMM), but can discovery descriptive behaviors that can be easily sampled. Furthermore, we show that through purely reward-free optimization, Skill DT is still competitive with supervised offline RL approaches on the D4RL benchmark. The code and videos can be found on our project page: https://github.com/shyamsn97/skill-dt