Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

NeurIPSOral2025

Authors: Felix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Ruan John de Kock, Juan Claude Formanek, Sasha Abramowitz, Omayma Mahjoub, Wiem Khlifi, Simon Verster Du Toit, Louay Ben Nessir, Refiloe Shabe, Arnol Manuel Fokam, Siddarth Singh, Ulrich Armel Mbou Sob, Arnu Pretorius
Affiliation: InstaDeep
Venue: NeurIPS 2025
Track: Oral

TL;DR

Using search strategies at inference-time can provide massive performance boost on numerous complex reinforcement learning tasks, within only a couple seconds of execution time.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

reinforcement learning

← All NeurIPS 2025 Oral papers · Browse the whole archive