English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Off-policy model-free deep reinforcement learning methods using previouslycollected data can improve sample efficiency over on-policy policy gradienttechniques. On the other hand, on-policy algorithms are often more stable andeasier to use. This paper examines, both theoretically and empirically,approaches to merging on- and off-policy updates for deep reinforcementlearning. Theoretical results show that off-policy updates with a valuefunction estimator can be interpolated with on-policy policy gradient updateswhilst still satisfying performance bounds. Our analysis uses control variatemethods to produce a family of policy gradient algorithms, with severalrecently proposed algorithms being special cases of this family. We thenprovide an empirical comparison of these techniques with the remainingalgorithmic details fixed, and show how different mixing of off-policy gradientestimates with on-policy samples contribute to improvements in empiricalperformance. The final algorithm provides a generalization and unification ofexisting deep policy gradient techniques, has theoretical guarantees on thebias introduced by off-policy updates, and improves on the state-of-the-artmodel-free deep RL methods on a number of OpenAI Gym continuous controlbenchmarks.

Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning