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

Offline reinforcement learning (RL) methodologies enforce constraints on thepolicy to adhere closely to the behavior policy, thereby stabilizing valuelearning and mitigating the selection of out-of-distribution (OOD) actionsduring test time. Conventional approaches apply identical constraints for bothvalue learning and test time inference. However, our findings indicate that theconstraints suitable for value estimation may in fact be excessivelyrestrictive for action selection during test time. To address this issue, wepropose a Mildly Constrained Evaluation Policy (MCEP) for test time inferencewith a more constrained target policy for value estimation. Since the targetpolicy has been adopted in various prior approaches, MCEP can be seamlesslyintegrated with them as a plug-in. We instantiate MCEP based on TD3-BC[Fujimoto and Gu, 2021] and AWAC [Nair et al., 2020] algorithms. The empiricalresults on MuJoCo locomotion tasks show that the MCEP significantly outperformsthe target policy and achieves competitive results to state-of-the-art offlineRL methods. The codes are open-sourced at https://github.com/egg-west/MCEP.git.

Mildly Constrained Evaluation Policy for Offline Reinforcement Learning