# Q-value Regularized Decision ConvFormer for Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2409.08062 · HTML: https://mlsanity.com/paper/2409.08062/

## Key facts

- Cited by 4 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 16 of its 18 references that are in the map.
- First posted on arXiv 12 Sep 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, 16 of 16)

- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [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)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL](https://mlsanity.com/paper/2209.03993/) (2022)
- [When does return-conditioned supervised learning work for offline reinforcement learning?](https://mlsanity.com/paper/2206.01079/) (2022)
- [Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes](https://mlsanity.com/paper/2211.15144/) (2022)
- [Elastic Decision Transformer](https://mlsanity.com/paper/2307.02484/) (2023)
- [You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments](https://mlsanity.com/paper/2205.15967/) (2022)
- [Q-value Regularized Transformer for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.17098/) (2024)
- [Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making](https://mlsanity.com/paper/2310.03022/) (2023)
- [Reinformer: Max-Return Sequence Modeling for Offline RL](https://mlsanity.com/paper/2405.08740/) (2024)

## Built on by (most cited first, 4 of 4)

- [CNMBI: Determining the Number of Clusters Using Center Pairwise Matching and Boundary Filtering](https://mlsanity.com/paper/2603.26744/) (2026)
- [Bridging Discrete Planning and Continuous Execution for Redundant Robot](https://mlsanity.com/paper/2604.02021/) (2026)
- [The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery](https://mlsanity.com/paper/2604.14176/) (2026)
- [T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation](https://mlsanity.com/paper/2606.30147/) (2026)

## Abstract (arXiv)

As a data-driven paradigm, offline reinforcement learning (Offline RL) has been formulated as sequence modeling, where the Decision Transformer (DT) has demonstrated exceptional capabilities. Unlike previous reinforcement learning methods that fit value functions or compute policy gradients, DT adjusts the autoregressive model based on the expected returns, past states, and actions, using a causally masked Transformer to output the optimal action. However, due to the inconsistency between the sampled returns within a single trajectory and the optimal returns across multiple trajectories, it is challenging to set an expected return to output the optimal action and stitch together suboptimal trajectories. Decision ConvFormer (DC) is easier to understand in the context of modeling RL trajectories within a Markov Decision Process compared to DT. We propose the Q-value Regularized Decision ConvFormer (QDC), which combines the understanding of RL trajectories by DC and incorporates a term that maximizes action values using dynamic programming methods during training. This ensures that the expected returns of the sampled actions are consistent with the optimal returns. QDC achieves excellent performance on the D4RL benchmark, outperforming or approaching the optimal level in all tested environments. It particularly demonstrates outstanding competitiveness in trajectory stitching capability.