An Optimistic Perspective on Offline Deep Reinforcement Learning
Jul 12, 2020
Speakers
Rishabh Agarwal
Speaker · 2 followers
Dale Schuurmans
Speaker · 2 followers
Mohammad Norouzi
Speaker · 1 follower
About
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…
Categories
AI & Data Science
Category · 10.8k presentations
About 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.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Sights and Sounds in 3D Spaces
Watch later
Ready Policy One: World Building Through Active Learning
Watch later
Amortised Learning by Wake-Sleep
Watch later
Reducing Sampling Error in Batch Temporal Difference Learning
Watch later
Brahma Pavse, …
Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
Watch later
Lijun Ding, …
