Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915810948153344 |
|---|---|
| author | Jung, Hoseong Son, Sungil Cho, Daesol Park, Jonghae Choi, Changhyun Kim, H. Jin |
| author_facet | Jung, Hoseong Son, Sungil Cho, Daesol Park, Jonghae Choi, Changhyun Kim, H. Jin |
| contents | Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex dynamics and represents the problem as a hybrid action space unifying discrete resource usage and continuous maneuvers. However, prior works on hybrid action space have not sufficiently captured the causal dependencies between resource usage and maneuvers. They have also overlooked the multi-modal nature of tactical decisions, both of which are critical in fast-evolving scenarios. In this paper, we propose TART, a Temporal Action Representation learning framework for Tactical resource control and subsequent maneuver generation. TART leverages contrastive learning based on a mutual information objective, designed to capture inherent temporal dependencies in resource-maneuver interactions. These learned representations are quantized into discrete codebook entries that condition the policy, capturing recurring tactical patterns and enabling multi-modal and temporally coherent behaviors. We evaluate TART in two domains where resource deployment is critical: (i) a maze navigation task where a limited budget of discrete actions provides enhanced mobility, and (ii) a high-fidelity air combat simulator in which an F-16 agent operates weapons and defensive systems in coordination with flight maneuvers. Across both domains, TART consistently outperforms hybrid-action baselines, demonstrating its effectiveness in leveraging limited resources and producing context-aware subsequent maneuvers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18716 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation Jung, Hoseong Son, Sungil Cho, Daesol Park, Jonghae Choi, Changhyun Kim, H. Jin Robotics Artificial Intelligence Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex dynamics and represents the problem as a hybrid action space unifying discrete resource usage and continuous maneuvers. However, prior works on hybrid action space have not sufficiently captured the causal dependencies between resource usage and maneuvers. They have also overlooked the multi-modal nature of tactical decisions, both of which are critical in fast-evolving scenarios. In this paper, we propose TART, a Temporal Action Representation learning framework for Tactical resource control and subsequent maneuver generation. TART leverages contrastive learning based on a mutual information objective, designed to capture inherent temporal dependencies in resource-maneuver interactions. These learned representations are quantized into discrete codebook entries that condition the policy, capturing recurring tactical patterns and enabling multi-modal and temporally coherent behaviors. We evaluate TART in two domains where resource deployment is critical: (i) a maze navigation task where a limited budget of discrete actions provides enhanced mobility, and (ii) a high-fidelity air combat simulator in which an F-16 agent operates weapons and defensive systems in coordination with flight maneuvers. Across both domains, TART consistently outperforms hybrid-action baselines, demonstrating its effectiveness in leveraging limited resources and producing context-aware subsequent maneuvers. |
| title | Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2602.18716 |