sim-to-real transfer
- Papers
- 13
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
13 papers in the last two months, against 0 in the two before.
Start here
Three papers to read first, in the order they came out- 1Regularised reinforcement learning boosts policy robustness in sim-to-real transfer
Regularised reinforcement learning improves real-world policy deployment through better robustness to the sim-to-real gap.
Oct 2026 - 2Soccer-playing humanoid robot learns four skills from human motion data
SoccerBot is a humanoid soccer system that uses human motion data to learn a single policy for moving, dribbling, trapping, and kicking with human-like motion.
Nov 2026 - 3Humanoid robots open round doorknobs without real training
Tactile-driven motor adaptation substantially outperforms standard methods for zero-shot sim-to-real humanoid doorknob opening.
Nov 2026
How fast it is moving
Often studied with
reinforcement learningA machine learning method where an agent learns to make sequences of decisions by receiving rewards or penalties for its actions.5 togetherprivileged informationInformation available only during training that improves performance but is not accessible at inference.3 togetheragent-driven simulationAutonomous agents automatically generate, control, or extend simulations to improve accuracy, interactivity, or performance.2 togetherWho is working on it
The papers
Most central to this idea first, not most recent.
- Big Techcs.RO
Humanoid robots open round doorknobs without real training
Tactile-driven motor adaptation substantially outperforms standard methods for zero-shot sim-to-real humanoid doorknob opening.
Amazon, Rice University · Nov 2026
- Top Universitycs.RO
Soccer-playing humanoid robot learns four skills from human motion data
SoccerBot is a humanoid soccer system that uses human motion data to learn a single policy for moving, dribbling, trapping, and kicking with human-like motion.
University of Science and Technology of China, State Key Laboratory of General Artificial Intelligence, BIGAI · Nov 2026
- Big Techcs.LG
Regularised reinforcement learning boosts policy robustness in sim-to-real transfer
Regularised reinforcement learning improves real-world policy deployment through better robustness to the sim-to-real gap.
Mila - Québec AI Institute, Polytechnique Montréal · Oct 2026
- Academiccs.RO
One-camera humanoids learn to catch objects they have never seen
A humanoid robot can catch unseen objects with underhand and overhand throws using one camera.
UC San Diego, Harvey Mudd College · Oct 2026
- Big Techcs.RO
Simulation-first framework lets coding agents learn real robot skills in 10 minutes
SimEX lets coding agents learn real robot skills by first practicing in simulation and then adapting with only 10 minutes of physical trials.
Amazon FAR, University of Texas at Austin · Oct 2026
- Big Techcs.RO
Robots can reorient objects from pictures without tracking their pose
A robot hand policy using only camera images and joint angles, with goals as images instead of object poses, reorients objects and transfers from simulation to real hands.
ETH Zurich, NVIDIA · Nov 2026
- Big Techcs.RO
Robots can better balance precise movement and recovery from disturbances
Energy-based policy orchestration jointly selects and refines policy-goal pairs to improve feasibility and tracking in hierarchical robot control.
Harvard University, Amazon Frontier AI & Robotics · Nov 2026
- Big Techcs.RO
Robots can learn hidden billiards physics by choosing their own shots
An agent that actively probes where its physics simulation is least accurate can learn a scene's hidden contact physics and predict real billiard outcomes far more accurately.
Stanford University, ETH Zurich · Nov 2026
- Industrycs.RO
Simulation training lets a pretrained model control robots on unfamiliar tasks
A pretrained vision-language model can learn robot motion entirely in simulation and transfer to real tasks and a new robot embodiment.
Luma AI · Oct 2026
- Big Techcs.RO
Adaptive sampling helps million-environment robot training solve harder tasks
Sampling task configurations where a policy has moderate success rates lets massively parallel robot RL solve harder tasks.
University of Washington, NVIDIA · Oct 2026
- Big Techcs.LG
Simulation priors speed adaptation of model-based autonomous racing controllers
Prior-Informed Adaptation (PIA) uses structured simulation priors for rapid adaptation in model-based RL for autonomous racing.
Toyota Research Institute, University of California San Diego (UCSD) · Oct 2026
- Big Techcs.RO
One Human Demonstration Can Seed Adaptable Dexterous Robot Skills
Training one goal-conditioned policy with dense human-motion tracking and sparse off-reference goals yields dexterous skills that preserve functional behavior while adapting to new states and targets.
Carnegie Mellon University, NVIDIA · Oct 2026
- Top Universitycs.LG
Multi-Fidelity Control Variates Stabilize Data-Scarce Reinforcement Learning
Multi-fidelity policy gradients stabilize data-scarce on-policy RL by using biased low-fidelity data as a variance-reducing control variate.
University of Texas at Austin, University of British Columbia · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.