CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915769908985856 |
|---|---|
| author | Alinejad, Mahyar Wang, Yue Atia, George |
| author_facet | Alinejad, Mahyar Wang, Yue Atia, George |
| contents | Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical guidance but fails to transfer long-term strategic knowledge, while automaton-based methods capture task structure but lack fine-grained action guidance. This paper introduces Context-Aware Distillation with Experience-gated Transfer (CADENT), a framework that unifies strategic automaton-based knowledge with tactical policy-level knowledge into a coherent guidance signal. CADENT's key innovation is an experience-gated trust mechanism that dynamically weighs teacher guidance against the student's own experience at the state-action level, enabling graceful adaptation to target domain specifics. Across challenging environments, from sparse-reward grid worlds to continuous control tasks, CADENT achieves 40-60\% better sample efficiency than baselines while maintaining superior asymptotic performance, establishing a robust approach for adaptive knowledge transfer in RL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02532 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning Alinejad, Mahyar Wang, Yue Atia, George Machine Learning Artificial Intelligence Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical guidance but fails to transfer long-term strategic knowledge, while automaton-based methods capture task structure but lack fine-grained action guidance. This paper introduces Context-Aware Distillation with Experience-gated Transfer (CADENT), a framework that unifies strategic automaton-based knowledge with tactical policy-level knowledge into a coherent guidance signal. CADENT's key innovation is an experience-gated trust mechanism that dynamically weighs teacher guidance against the student's own experience at the state-action level, enabling graceful adaptation to target domain specifics. Across challenging environments, from sparse-reward grid worlds to continuous control tasks, CADENT achieves 40-60\% better sample efficiency than baselines while maintaining superior asymptotic performance, establishing a robust approach for adaptive knowledge transfer in RL. |
| title | CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.02532 |