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

Sparse rewards present a difficult problem in reinforcement learning and maybe inevitable in certain domains with complex dynamics such as real-worldrobotics. Hindsight Experience Replay (HER) is a recent replay memorydevelopment that allows agents to learn in sparse settings by altering memoriesto show them as successful even though they may not be. While, empirically, HERhas shown some success, it does not provide guarantees around the makeup ofsamples drawn from an agent's replay memory. This may result in minibatchesthat contain only memories with zero-valued rewards or agents learning anundesirable policy that completes HER-adjusted goals instead of the actualgoal.  In this paper, we introduce Or Your Money Back (OYMB), a replay memorysampler designed to work with HER. OYMB improves training efficiency in sparsesettings by providing a direct interface to the agent's replay memory thatallows for control over minibatch makeup, as well as a preferential lookupscheme that prioritizes real-goal memories before HER-adjusted memories. Wetest our approach on five tasks across three unique environments. Our resultsshow that using HER in combination with OYMB outperforms using HER alone andleads to agents that learn to complete the real goal more quickly.

Sample Efficiency in Sparse Reinforcement Learning: Or Your Money Back