Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909642372677632 |
|---|---|
| author | Panagopoulos, Dimitris Perrusquia, Adolfo Guo, Weisi |
| author_facet | Panagopoulos, Dimitris Perrusquia, Adolfo Guo, Weisi |
| contents | Autonomous systems operating in high-stakes search-and-rescue (SAR) missions must continuously gather mission-critical information while flexibly adapting to shifting operational priorities. We propose CA-MIQ (Context-Aware Max-Information Q-learning), a lightweight dual-critic reinforcement learning (RL) framework that dynamically adjusts its exploration strategy whenever mission priorities change. CA-MIQ pairs a standard extrinsic critic for task reward with an intrinsic critic that fuses state-novelty, information-location awareness, and real-time priority alignment. A built-in shift detector triggers transient exploration boosts and selective critic resets, allowing the agent to re-focus after a priority revision. In a simulated SAR grid-world, where experiments specifically test adaptation to changes in the priority order of information types the agent is expected to focus on, CA-MIQ achieves nearly four times higher mission-success rates than baselines after a single priority shift and more than three times better performance in multiple-shift scenarios, achieving 100% recovery while baseline methods fail to adapt. These results highlight CA-MIQ's effectiveness in any discrete environment with piecewise-stationary information-value distributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06786 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain Panagopoulos, Dimitris Perrusquia, Adolfo Guo, Weisi Artificial Intelligence Autonomous systems operating in high-stakes search-and-rescue (SAR) missions must continuously gather mission-critical information while flexibly adapting to shifting operational priorities. We propose CA-MIQ (Context-Aware Max-Information Q-learning), a lightweight dual-critic reinforcement learning (RL) framework that dynamically adjusts its exploration strategy whenever mission priorities change. CA-MIQ pairs a standard extrinsic critic for task reward with an intrinsic critic that fuses state-novelty, information-location awareness, and real-time priority alignment. A built-in shift detector triggers transient exploration boosts and selective critic resets, allowing the agent to re-focus after a priority revision. In a simulated SAR grid-world, where experiments specifically test adaptation to changes in the priority order of information types the agent is expected to focus on, CA-MIQ achieves nearly four times higher mission-success rates than baselines after a single priority shift and more than three times better performance in multiple-shift scenarios, achieving 100% recovery while baseline methods fail to adapt. These results highlight CA-MIQ's effectiveness in any discrete environment with piecewise-stationary information-value distributions. |
| title | Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.06786 |