The agent performs well in simulation.
When deployed in the real world, it makes strange decisions.
The physics is slightly different.
Small changes lead to big failures.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
The agent performs well in simulation.
When deployed in the real world, it makes strange decisions.
The physics is slightly different.
Small changes lead to big failures.
This happens because simulations never perfectly match reality. The model learns simulation-specific dynamics that do not transfer.
This is known as the sim-to-real gap. Even tiny differences in friction, timing, or noise can break learned policies.
Domain randomization and real-world fine-tuning help close this gap.
Common mistakes:
Overfitting to simulation
No noise injection
No real-world adaptation
The practical takeaway is that real environments require real data.