Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.15427 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909435802157056 |
|---|---|
| author | Kumawat, Hemant Mukhopadhyay, Saibal |
| author_facet | Kumawat, Hemant Mukhopadhyay, Saibal |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15427 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AdaCred: Adaptive Causal Decision Transformers with Feature Crediting Kumawat, Hemant Mukhopadhyay, Saibal Machine Learning Robotics 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. |
| title | AdaCred: Adaptive Causal Decision Transformers with Feature Crediting |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2412.15427 |