Cover Image

Closing the Sim2Real Performance Gap in RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Anand, Akhil S, Sawant, Shambhuraj, Hoffmann, Jasper, Reinhardt, Dirk, Gros, Sebastien
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

All AI Models are Wrong, but Some are Optimal
by: Anand, Akhil S, et al.
Published: (2025)

Data-Driven Predictive Control and MPC: Do we achieve optimality?
by: Anand, Akhil S, et al.
Published: (2024)

Economic Model Predictive Control as a Solution to Markov Decision Processes
by: Reinhardt, Dirk, et al.
Published: (2024)

Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification
by: Reiter, Rudolf, et al.
Published: (2025)

Differentiable Nonlinear Model Predictive Control
by: Frey, Jonathan, et al.
Published: (2025)

Direct transfer of optimized controllers to similar systems using dimensionless MPC
by: Hromatko, Josip Kir, et al.
Published: (2025)

CORL: Reinforcement Learning of MILP Policies Solved via Branch and Bound
by: Anand, Akhil S, et al.
Published: (2025)

Learning to Dock: A Simulation-based Study on Closing the Sim2Real Gap in Autonomous Underwater Docking
by: Chang, Kevin, et al.
Published: (2025)

Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?
by: Markgraf, Hannah, et al.
Published: (2025)

Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation
by: Fey, Nolan, et al.
Published: (2025)

Mind the Sim-to-Real Gap & Think Like a Scientist
by: Parikh, Harsh, et al.
Published: (2026)

Application of Soft Actor-Critic Algorithms in Optimizing Wastewater Treatment with Time Delays Integration
by: Mohammadi, Esmaeel, et al.
Published: (2024)

Bridging the Sim-to-Real Gap in Reinforcement Learning-Based Industrial Dispatching through Execution Semantics
by: Hoss, Jonathan, et al.
Published: (2026)

Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion
by: Lomurno, Eugenio, et al.
Published: (2026)

SafePowerGraph-HIL: Real-Time HIL Validation of Heterogeneous GNNs for Bridging Sim-to-Real Gap in Power Grids
by: Ma, Aoxiang, et al.
Published: (2025)

X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
by: Dan, Prithwish, et al.
Published: (2025)

Small transformer architectures for task switching
by: Gros, Claudius
Published: (2025)

Reorganizing attention-space geometry with expressive attention
by: Gros, Claudius
Published: (2024)

Watch Less, Feel More: Sim-to-Real RL for Generalizable Articulated Object Manipulation via Motion Adaptation and Impedance Control
by: Do, Tan-Dzung, et al.
Published: (2025)

RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
by: Lei, Kun, et al.
Published: (2025)

IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections
by: Ranjan, Yash, et al.
Published: (2025)

CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning
by: Rowe, Luke, et al.
Published: (2024)

Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)
by: Müller, Nicola J., et al.
Published: (2026)

Digital Twin Synchronization: Bridging the Sim-RL Agent to a Real-Time Robotic Additive Manufacturing Control
by: Ali, Matsive, et al.
Published: (2025)

Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning
by: Hu, Jiajun, et al.
Published: (2026)

Closing Gaps: An Imputation Analysis of ICU Vital Signs
by: Turubayev, Alisher, et al.
Published: (2025)

H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps
by: Niu, Haoyi, et al.
Published: (2023)

Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
by: Seo, Younggyo, et al.
Published: (2025)

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
by: Wang, Jiaxu, et al.
Published: (2026)

Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior
by: Gros, Timo P., et al.
Published: (2025)

Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
by: Torne, Marcel, et al.
Published: (2024)

DrEureka: Language Model Guided Sim-To-Real Transfer
by: Ma, Yecheng Jason, et al.
Published: (2024)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
by: Terence, Ng Wen Zheng, et al.
Published: (2024)

RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$
by: Bhatia, Abhinav, et al.
Published: (2023)

Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
by: Nunez, Jeanmely Rojas, et al.
Published: (2026)

Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
by: Kim, Youngsung
Published: (2026)

TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction
by: Jiang, Yunfan, et al.
Published: (2024)

NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios
by: Gao, Songyi, et al.
Published: (2025)

The Effective Horizon Explains Deep RL Performance in Stochastic Environments
by: Laidlaw, Cassidy, et al.
Published: (2023)

On the Mathematical Impossibility of Safe Universal Approximators
by: Yao, Jasper
Published: (2025)