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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In Markov games, playing against non-stationary opponents with learningability is still challenging for reinforcement learning (RL) agents, becausethe opponents can evolve their policies concurrently. This increases thecomplexity of the learning task and slows down the learning speed of the RLagents. This paper proposes efficient use of rough heuristics to speed uppolicy learning when playing against concurrent learners. Specifically, wepropose an algorithm that can efficiently learn explainable and generalizedaction selection rules by taking advantages of the representation ofquantitative heuristics and an opponent model with an eXtended classifiersystem (XCS) in zero-sum Markov games. A neural network is used to model theopponent from their behaviors and the corresponding policy is inferred foraction selection and rule evolution. In cases of multiple heuristic policies,we introduce the concept of Pareto optimality for action selection. Besides,taking advantages of the condition representation and matching mechanism ofXCS, the heuristic policies and the opponent model can provide guidance forsituations with similar feature representation. Furthermore, we introduce anaccuracy-based eligibility trace mechanism to speed up rule evolution, i.e.,classifiers that can match the historical traces are reinforced according totheir accuracy. We demonstrate the advantages of the proposed algorithm overseveral benchmark algorithms in a soccer and a thief-and-hunter scenarios.

Efficient Use of heuristics for accelerating XCS-based Policy Learning in Markov Games