Latent Skill Planning for Exploration and Transfer
Mai 3, 2021
Sprecher:innen
Homanga Bharadhwaj
Sprecher:in · 0 Follower:innen
Danijar Hafner
Sprecher:in · 6 Follower:innen
Animesh Garg
Sprecher:in · 0 Follower:innen
Florian Shkurti
Sprecher:in · 0 Follower:innen
Über
To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture general behaviors that can apply to new tasks. In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent. Specifically, we leverage the idea of partial amortization for fast adaptation at test time. For this, actions are produced by a policy that is learned over time while the skills it conditions on are chosen using online planning. We demonstrate the benefits of our design decisions across a suite of challenging locomotion tasks and demonstrate improved sample efficiency in single tasks as well as in transfer from one task to another, as compared to competitive baselines. Videos are available at: https://sites.google.com/view/partial-amortization/homeTo quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture general behaviors that can apply to new tasks. In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent. Specifically, we leverage the idea of partial amortization for fast adaptation at test time. For t…
Kategorien
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
Über ICLR 2021
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Optimism in Reinforcement Learning with Generalized Linear Function Approximation
Später ansehen
Yining Wang, …
Oral Session 5
Später ansehen
Reinforcement Learning with Prototypical Representations
Später ansehen
Denis Yarats, …
Panel Discussion
Später ansehen
Eric Rice, …
Improving Robustness to Label Noise in Text Classification via Noise Modeling
Später ansehen
Considerations for Practical Learned Video Coding
Später ansehen
Oren Rippel, …