Actor-Critic with Active Importance Sampling
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_ | 1866918489136037888 |
|---|---|
| author | Molaei, Majid Paczolay, Gabor Papini, Matteo Metelli, Alberto Maria Restelli, Marcello |
| author_facet | Molaei, Majid Paczolay, Gabor Papini, Matteo Metelli, Alberto Maria Restelli, Marcello |
| contents | This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient variance while preserving unbiased gradient estimates. Using importance sampling principles, the algorithm adapts the behavior policy toward efficient data collection distributions aligned with target policy gradients.
For continuous action spaces, AISAC employs Gaussian behavior policies optimized through cross-entropy minimization. We provide theoretical analysis demonstrating variance reduction and unbiasedness. Experiments on Inverted Pendulum and Half Cheetah tasks show improved learning speed, sample efficiency, and training stability compared to standard Actor-Critic methods.
Results indicate that optimizing the behavior policy improves both target policy updates and critic estimation accuracy across different hyperparameter settings. AISAC accelerates convergence and stabilizes reinforcement learning training, making it promising for real-world applications. Future work includes integration with advanced algorithms such as Soft Actor-Critic and TD3 for more complex environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07094 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Actor-Critic with Active Importance Sampling Molaei, Majid Paczolay, Gabor Papini, Matteo Metelli, Alberto Maria Restelli, Marcello Machine Learning This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient variance while preserving unbiased gradient estimates. Using importance sampling principles, the algorithm adapts the behavior policy toward efficient data collection distributions aligned with target policy gradients. For continuous action spaces, AISAC employs Gaussian behavior policies optimized through cross-entropy minimization. We provide theoretical analysis demonstrating variance reduction and unbiasedness. Experiments on Inverted Pendulum and Half Cheetah tasks show improved learning speed, sample efficiency, and training stability compared to standard Actor-Critic methods. Results indicate that optimizing the behavior policy improves both target policy updates and critic estimation accuracy across different hyperparameter settings. AISAC accelerates convergence and stabilizes reinforcement learning training, making it promising for real-world applications. Future work includes integration with advanced algorithms such as Soft Actor-Critic and TD3 for more complex environments. |
| title | Actor-Critic with Active Importance Sampling |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.07094 |