← Search

Manon Flageat

2 accepted papers

2024

Beyond Expected Return: Accounting for Policy Reproducibility When Evaluating Reinforcement Learning Algorithms

AAAI 2024technical

Many applications in Reinforcement Learning (RL) usually have noise or stochasticity present in the environment. Beyond their impact on learning, these uncertainties lead the exact same policy to perform differently, i.e. yield different return, from one roll-out to another. Common evaluation proced…

Cited by 4SourcePDFScholar