paper-with-me

홈 › Papers

Certificate-Guided Evaluation of Reinforcement Learning Generalization

2026-05-30 · Vignesh Subramanian, Đorđe Žikelić, Suguman Bansal arxiv

This work presents a logic-driven framework to evaluate the performance of reinforcement learning (RL) algorithms in their ability to generalize to unseen tasks. Our framework defines a family of inductive reach-avoid tasks, characterized by structural similarities in task dynamics, enabling evaluation of generalization capabilities. We introduce a neural certificate function that validates trajectories generated by RL algorithms by enforcing key conditions, thereby serving as a litmus test for RL generalization. We empirically demonstrate our method's capability in certifying generalization for several state-of-the-art generalizable RL algorithms on challenging continuous environments. Our results show that a lower percentage of certificate function violations correlates with a higher number of test tasks successfully solved, highlighting the effectiveness of our framework in evaluating and distinguishing generalization capabilities of RL algorithms. This work provides a principled approach for benchmarking RL generalization.

📄 PDF Abstract BibTeX arXiv:2606.00840

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

PAC-Bayesian Reinforcement Learning Trains Generalizable Policies

2025-10-12 · Abdelkrim Zitouni, Mehdi Hennequin, Juba Agoun, Ryan Horache 외 arxiv

We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in o…

Reinforcement LearningContinuous Control

Certificate-Guided Pruning for Stochastic Lipschitz Optimization

2026-01-28 · Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma arxiv

We study black-box optimization of Lipschitz functions under noisy evaluations. Existing adaptive discretization methods implicitly avoid suboptimal regions but do not provide explicit certificates of optimality or measu…

k-Inductive Neural Barrier Certificates for Unknown Nonlinear Dynamics

2026-05-19 · Ben Wooding, Hongchao Zhang, Taylor T. Johnson, Abolfazl Lavaei arxiv

While conventional (k=1) discrete-time barrier certificate conditions impose strict safety constraints by requiring the function to be non-increasing at every step, k-inductive barrier certificates relax this by allowing…

Learning Stability Certificates from Data

2020-08-13 · Nicholas M. Boffi, Stephen Tu, Nikolai Matni, Jean-Jacques E. Slotine 외

Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guarantees a desired property. However, algor…

Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning

2021-11-15 · Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng 외

Safety is the major consideration in controlling complex dynamical systems using reinforcement learning (RL), where the safety certificate can provide provable safety guarantee. A valid safety certificate is an energy fu…

reinforcement-learningReinforcement Learning (RL)valid