# AdaCred: Adaptive Causal Decision Transformers with Feature Crediting

arXiv: https://arxiv.org/abs/2412.15427 · HTML: https://mlsanity.com/paper/2412.15427/

## Key facts

- Cited by 1 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 10 of its 23 references that are in the map.
- First posted on arXiv 19 Dec 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, 10 of 10)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Distributional Reinforcement Learning with Quantile Regression](https://mlsanity.com/paper/1710.10044/) (2017)
- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment](https://mlsanity.com/paper/2307.03864/) (2023)
- [Radar Guided Dynamic Visual Attention for Resource-Efficient RGB Object Detection](https://mlsanity.com/paper/2206.01772/) (2022)
- [STEMFold: Stochastic Temporal Manifold for Multi-Agent Interactions in the Presence of Hidden Agents](https://mlsanity.com/paper/2401.14522/) (2024)
- [RoboKoop: Efficient Control Conditioned Representations from Visual Input in Robotics using Koopman Operator](https://mlsanity.com/paper/2409.03107/) (2024)

## Built on by (most cited first, 1 of 1)

- [Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges](https://mlsanity.com/paper/2502.02692/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the environment in offline RL settings. However, these models tend to over-rely on memorizing long-term representations, which impairs their ability to effectively attribute importance to trajectories and learned representations based on task-specific relevance. In this work, we introduce AdaCred, a novel approach that represents trajectories as causal graphs built from short-term action-reward-state sequences. Our model adaptively learns control policy by crediting and pruning low-importance representations, retaining only those most relevant for the downstream task. Our experiments demonstrate that AdaCred-based policies require shorter trajectory sequences and consistently outperform conventional methods in both offline reinforcement learning and imitation learning environments.