pith. sign in

arxiv: 1905.13559 · v1 · pith:Q62XOCWMnew · submitted 2019-05-29 · 💻 cs.LG · cs.AI· stat.ML

Advantage Amplification in Slowly Evolving Latent-State Environments

classification 💻 cs.LG cs.AIstat.ML
keywords environmentsadvantageamplificationhurdleslatent-statemethodsseveralslowly
0
0 comments X
read the original abstract

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general principle of advantage amplification that can overcome these hurdles through the use of temporal abstraction. We propose several aggregation methods and prove they induce amplification in certain settings. We also bound the loss in optimality incurred by our methods in environments where latent state evolves slowly and demonstrate their performance empirically in a stylized user-modeling task.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.