The Benefits of Model-Based Generalization in Reinforcement Learning
Jul 24, 2023
Sprecher:innen
Kenny Young
Sprecher:in · 0 Follower:innen
Aditya Ramesh
Sprecher:in · 1 Follower:in
Louis Kirsch
Sprecher:in · 0 Follower:innen
Jürgen Schmidhuber
Sprecher:in · 2 Follower:innen
Über
Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind of model, which has proved effective at improving the stability and efficiency of deep RL. In principle, a learned parametric model could improve on ER by generalizing from real experience to augment the dataset with additional plausible experience. However, given that learned value functions can also generalize, it is not immediately obvious why model generalization should be better. Here, we provide theoretical and empirical insight into when, and how, we can expect data generated by a learned model to be useful. First, we provide a simple theorem motivating how learning a model as an intermediate step can narrow down the set of possible value functions more than learning a value function directly from data using the Bellman equation. Second, we provide an illustrative example showing empirically how a similar effect occurs in a more concrete setting with neural network function approximation. Finally, we provide extensive experiments showing the benefit of model-based learning for online RL in environments with combinatorial complexity, but factored structure that allows a learned model to generalize. In these experiments, we take care to control for other factors in order to isolate, insofar as possible, the benefit of using experience generated by a learned model relative to ER alone.Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind of model, which has proved effective at improving the stability and efficiency of deep RL. In principle, a learned parametric model could improve on ER by generalizing from real experience to augment the dataset with additional plausible experience. However, giv…
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
Cut your Losses with Squentropy
Später ansehen
Like Hui, …
Modeling Accurate Long Rollouts with Temporal Neural PDE Solvers
Später ansehen
Invariant Slot Attention
Später ansehen
Ondrej Biza, …
Temporally Consistent Transformers for Video Generation
Später ansehen
Wilson Yan, …
The Societal Impacts of AI
Später ansehen
Sanmi Koyejo, …