Papers with Code 아카이브
Safe Exploration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Safe Exploration is an approach to collect ground truth data by safely interacting with the environment.
Source: Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/AgrawalAmey/safe-explorer
https://github.com/Data-Science-in-Mechanical-Engineering/Contextual-GoSafe
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
https://github.com/IBM/vsrl-framework
Verifiably Safe Exploration for End-to-End Reinforcement Learning
https://github.com/anyboby/mujoco_safety_gym
Safe Continuous Control with Constrained Model-Based Policy Optimization
https://github.com/huiyulhy/safe-control-gym
https://github.com/kollerlukas/safe-explorer
https://github.com/mahaitongdae/safety_index_synthesis
Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety
https://github.com/mateuszjurewicz/bornhack_ml_crashcourse
https://github.com/n-akram/SafeML
SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure
https://github.com/sharisun18/Absent_Supervisor_Env
https://github.com/ustc-arg/safe-robot-learning-competition
https://github.com/utiasDSL/safe-control-gym
https://github.com/zlr20/saferl_kit
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.