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 propose a new policy iteration theory as an important extension of softpolicy iteration and Soft Actor-Critic (SAC), one of the most efficient modelfree algorithms for deep reinforcement learning. Supported by the new theory,arbitrary entropy measures that generalize Shannon entropy, such as Tsallisentropy and Renyi entropy, can be utilized to properly randomize actionselection while fulfilling the goal of maximizing expected long-term rewards.Our theory gives birth to two new algorithms, i.e., Tsallis entropyActor-Critic (TAC) and Renyi entropy Actor-Critic (RAC). Theoretical analysisshows that these algorithms can be more effective than SAC. Moreover, they pavethe way for us to develop a new Ensemble Actor-Critic (EAC) algorithm in thispaper that features the use of a bootstrap mechanism for deep environmentexploration as well as a new value-function based mechanism for high-levelaction selection. Empirically we show that TAC, RAC and EAC can achievestate-of-the-art performance on a range of benchmark control tasks,outperforming SAC and several cutting-edge learning algorithms in terms of bothsample efficiency and effectiveness.

Off-Policy Actor-Critic in an Ensemble: Achieving Maximum General Entropy and Effective Environment Exploration in Deep Reinforcement Learning