While imitation learning requires access to high-quality data, offline reinforcement learning (RL) should, in principle, perform similarly or better with substantially lower data quality by using a value function. However, current results indicate that offline RL often performs worse than imitation learning, and it is often unclear what holds back the performance of offline RL. Motivated by this observation, we aim to understand the bottlenecks in current offline RL algorithms. While poor performance of offline RL is typically attributed to an imperfect value function, we ask: is the main bottleneck of offline RL indeed in learning the value function, or something else? To answer this question, we perform a systematic empirical study of (1) value learning, (2) policy extraction, and (3) policy generalization in offline RL problems, analyzing how these components affect performance.

Edit note: We know data preparation requires a ton of work and thought. In this provocative article, Hugo Bowne-Anderson provides a formal rationale for why that work matters, why data preparation is particularly important for reanalyzing data, and why you should stay focused on the question you hope to answer. Along the way, Hugo introduces how tools and automation can help augment analysts and better enable real-time models. In a world focused on buzzword-driven models and algorithms, you'd be forgiven for forgetting about the unreasonable importance of data preparation and quality: your models are only as good as the data you feed them. This is the garbage in, garbage out principle: flawed data going in leads to flawed results, algorithms, and business decisions. If a self-driving car's decision-making algorithm is trained on data of traffic collected during the day, you wouldn't put it on the roads at night.

Check out the Strata Data and Artificial Intelligence conference series, which cover the topics and key issues discussed in the Data Show Podcast. Subscribe to the O'Reilly Data Show Podcast to explore the opportunities and techniques driving big data, data science, and AI. Find us on Stitcher, TuneIn, iTunes, SoundCloud, RSS. For the end-of-year holiday episode of the Data Show, I turned the tables on Data Show host Ben Lorica to talk about trends in big data, machine learning, and AI, and what to look for in 2019. Lorica also showcased some highlights from our upcoming Strata Data and Artificial Intelligence conferences.