# Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

arXiv: https://arxiv.org/abs/2410.24108 · HTML: https://mlsanity.com/paper/2410.24108/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 67 of its 76 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

- Offline RL and imitation learning from data / [Decision transformers and sequence modeling](https://mlsanity.com/offlinerl/decision-transformers-and-sequence-modeling/)

## Builds on (most cited first, 30 of 67)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [Multi-Game Decision Transformers](https://mlsanity.com/paper/2205.15241/) (2022)
- [Online Decision Transformer](https://mlsanity.com/paper/2202.05607/) (2022)
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://mlsanity.com/paper/2112.10751/) (2021)
- [Verifiable Reinforcement Learning via Policy Extraction](https://mlsanity.com/paper/1805.08328/) (2018)

## Built on by (most cited first, 8 of 8)

- [Behavioral Exploration: Learning to Explore via In-Context Adaptation](https://mlsanity.com/paper/2507.09041/) (2025)
- [Online Finetuning Decision Transformers with Pure RL Gradients](https://mlsanity.com/paper/2601.00167/) (2026)
- [Decoupling Return-to-Go for Efficient Decision Transformer](https://mlsanity.com/paper/2601.15953/) (2026)
- [Adjusting the Output of Decision Transformer with Action Gradient](https://mlsanity.com/paper/2510.05285/) (2025)
- [Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer](https://mlsanity.com/paper/2605.06104/) (2026)
- [Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning](https://mlsanity.com/paper/2605.29028/) (2026)
- [Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management](https://mlsanity.com/paper/2608.28878/) (2026)
- [Vision-Language-Action Autonomous Driving Agent with Language-based Memory](https://mlsanity.com/paper/2609.38641/) (2026)

## Abstract (arXiv)

Decision Transformers have recently emerged as a new and compelling paradigm for offline Reinforcement Learning (RL), completing a trajectory in an autoregressive way. While improvements have been made to overcome initial shortcomings, online finetuning of decision transformers has been surprisingly under-explored. The widely adopted state-of-the-art Online Decision Transformer (ODT) still struggles when pretrained with low-reward offline data. In this paper, we theoretically analyze the online-finetuning of the decision transformer, showing that the commonly used Return-To-Go (RTG) that's far from the expected return hampers the online fine-tuning process. This problem, however, is well-addressed by the value function and advantage of standard RL algorithms. As suggested by our analysis, in our experiments, we hence find that simply adding TD3 gradients to the finetuning process of ODT effectively improves the online finetuning performance of ODT, especially if ODT is pretrained with low-reward offline data. These findings provide new directions to further improve decision transformers.