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

We consider the offline constrained reinforcement learning (RL) problem, inwhich the agent aims to compute a policy that maximizes expected return whilesatisfying given cost constraints, learning only from a pre-collected dataset.This problem setting is appealing in many real-world scenarios, where directinteraction with the environment is costly or risky, and where the resultingpolicy should comply with safety constraints. However, it is challenging tocompute a policy that guarantees satisfying the cost constraints in the offlineRL setting, since the off-policy evaluation inherently has an estimation error.In this paper, we present an offline constrained RL algorithm that optimizesthe policy in the space of the stationary distribution. Our algorithm,COptiDICE, directly estimates the stationary distribution corrections of theoptimal policy with respect to returns, while constraining the cost upperbound, with the goal of yielding a cost-conservative policy for actualconstraint satisfaction. Experimental results show that COptiDICE attainsbetter policies in terms of constraint satisfaction and return-maximization,outperforming baseline algorithms.

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation