$λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929259731222528 |
|---|---|
| author | Voelcker, Claas A Ahmadian, Arash Abachi, Romina Gilitschenski, Igor Farahmand, Amir-massoud |
| author_facet | Voelcker, Claas A Ahmadian, Arash Abachi, Romina Gilitschenski, Igor Farahmand, Amir-massoud |
| contents | The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning. While promising theoretical results have been established, the empirical performance of algorithms leveraging a decision-aware loss has been lacking, especially in continuous control problems. In this paper, we present a study on the necessary components for decision-aware reinforcement learning models and we showcase design choices that enable well-performing algorithms. To this end, we provide a theoretical and empirical investigation into algorithmic ideas in the field. We highlight that empirical design decisions established in the MuZero line of works, most importantly the use of a latent model, are vital to achieving good performance for related algorithms. Furthermore, we show that the MuZero loss function is biased in stochastic environments and establish that this bias has practical consequences. Building on these findings, we present an overview of which decision-aware loss functions are best used in what empirical scenarios, providing actionable insights to practitioners in the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_17366 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | $λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models Voelcker, Claas A Ahmadian, Arash Abachi, Romina Gilitschenski, Igor Farahmand, Amir-massoud Machine Learning Artificial Intelligence The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning. While promising theoretical results have been established, the empirical performance of algorithms leveraging a decision-aware loss has been lacking, especially in continuous control problems. In this paper, we present a study on the necessary components for decision-aware reinforcement learning models and we showcase design choices that enable well-performing algorithms. To this end, we provide a theoretical and empirical investigation into algorithmic ideas in the field. We highlight that empirical design decisions established in the MuZero line of works, most importantly the use of a latent model, are vital to achieving good performance for related algorithms. Furthermore, we show that the MuZero loss function is biased in stochastic environments and establish that this bias has practical consequences. Building on these findings, we present an overview of which decision-aware loss functions are best used in what empirical scenarios, providing actionable insights to practitioners in the field. |
| title | $λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2306.17366 |