An Optimistic Perspective on Offline Deep Reinforcement Learning
Jul 12, 2020
Sprecher:innen
Rishabh Agarwal
Řečník · 2 sledující
Dale Schuurmans
Řečník · 2 sledující
Mohammad Norouzi
Řečník · 1 sledující
Über
Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay experience of a DQN agent on 60 Atari 2600 games. We demonstrate that recent off-policy deep RL algorithms, even when trained solely on this replay dataset, outperform the fully trained DQN agent. To enhance generalization in the offline setting, we present Random Ensemble Mixture (REM), a robust Q-learning algorithm that enforces optimal Bellman consistency on random convex combinations of multiple Q-value estimates. Offline REM trained on the DQN replay dataset surpasses strong RL baselines. The results here present an optimistic view that robust RL algorithms used on sufficiently large and diverse offline datasets can result in high quality policies. The DQN replay dataset will be released to enable offline optimization of RL algorithms on a common ground.Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay experience of a DQN agent on 60 Atari 2600 games. We demonstrate that recent off-policy deep RL algorithms, even when trained solely on this replay dataset, outperform the fully trained DQN agent. To enhance generalization in the offline setting, we present Rand…
Kategorien
Umělá inteligence a data science
Kategorie · 10,8k prezentací
Über ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
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
Step-size Adaptation Using Exponentiated Gradient Updates
Zhlédnout později
Ehsan Amid, …
VFlow: More Expressive Generative Flows with Variational Data Augmentation
Zhlédnout později
Jianfei Chen, …
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Zhlédnout později
Constructive universal high-dimensional distribution generation through deep ReLU networks
Zhlédnout později
Speaker Panel
Zhlédnout později
Contributed Talk 3 - Talk
Zhlédnout později
Sungjin Ahn, …