Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Flageat, Manon, Lim, Bryan, Cully, Antoine
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Large Language Models as In-context AI Generators for Quality-Diversity
par: Lim, Bryan, et autres
Publié: (2024)

Enhancing MAP-Elites with Multiple Parallel Evolution Strategies
par: Flageat, Manon, et autres
Publié: (2023)

Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning
par: Faldor, Maxence, et autres
Publié: (2023)

Exploring the Performance-Reproducibility Trade-off in Quality-Diversity
par: Flageat, Manon, et autres
Publié: (2024)

Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
par: Peng, Nianli, et autres
Publié: (2023)

CAX: Cellular Automata Accelerated in JAX
par: Faldor, Maxence, et autres
Publié: (2024)

Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
par: Sinha, Abhijeet, et autres
Publié: (2026)

Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm
par: Lim, Yooseok, et autres
Publié: (2024)

Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
par: Goodall, Alexander W., et autres
Publié: (2025)

Policy Newton Algorithm in Reproducing Kernel Hilbert Space
par: Zhang, Yixian, et autres
Publié: (2025)

Dreaming in Code for Curriculum Learning in Open-Ended Worlds
par: Mitsides, Konstantinos, et autres
Publié: (2026)

Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations
par: Mitsides, Konstantinos, et autres
Publié: (2025)

Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces
par: Janmohamed, Hannah, et autres
Publié: (2025)

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
par: Grillotti, Luca, et autres
Publié: (2024)

R2L: Reliable Reinforcement Learning: Guaranteed Return & Reliable Policies in Reinforcement Learning
par: Farhi, Nadir
Publié: (2025)

Meta-Learning Reinforcement Learning for Crypto-Return Prediction
par: Wang, Junqiao, et autres
Publié: (2025)

Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
par: Kiyohara, Haruka, et autres
Publié: (2023)

Evaluation-Time Policy Switching for Offline Reinforcement Learning
par: Neggatu, Natinael Solomon, et autres
Publié: (2025)

Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
par: Kohler, Hector, et autres
Publié: (2025)

Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
par: Zhang, Jinouwen, et autres
Publié: (2024)

Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping
par: Lesy, Bavo, et autres
Publié: (2024)

Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data
par: Madhow, Sunil, et autres
Publié: (2023)

The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations
par: Lehmann, Matthias
Publié: (2024)

STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning
par: Chen, Sirui, et autres
Publié: (2023)

Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
par: Büchi, Hannes, et autres
Publié: (2026)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
par: Tu, Songjun, et autres
Publié: (2024)

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
par: Wang, Ruhan, et autres
Publié: (2024)

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
par: Zeng, Zhiyuan, et autres
Publié: (2024)

CUER: Corrected Uniform Experience Replay for Off-Policy Continuous Deep Reinforcement Learning Algorithms
par: Yenicesu, Arda Sarp, et autres
Publié: (2024)

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
par: Schoepp, Sheila, et autres
Publié: (2024)

From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity
par: Grillotti, Luca, et autres
Publié: (2025)

Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior
par: Perini, Lorenzo, et autres
Publié: (2024)

Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning
par: Cherukuri, Kalyan, et autres
Publié: (2025)

Moments Matter:Stabilizing Policy Optimization using Return Distributions
par: Jabs, Dennis, et autres
Publié: (2026)

SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation
par: Kiyohara, Haruka, et autres
Publié: (2023)

Reinforcement Learning for Durable Algorithmic Recourse
par: Ceccon, Marina, et autres
Publié: (2025)

MiWaves Reinforcement Learning Algorithm
par: Ghosh, Susobhan, et autres
Publié: (2024)

Agnostic Reinforcement Learning: Foundations and Algorithms
par: Li, Gene
Publié: (2025)

Return Capping: Sample-Efficient CVaR Policy Gradient Optimisation
par: Mead, Harry, et autres
Publié: (2025)

Beyond Rewards in Reinforcement Learning for Cyber Defence
par: Bates, Elizabeth, et autres
Publié: (2026)