befelix / SafeOpt
Safe Bayesian Optimization
☆140Updated last year
Related projects: ⓘ
- Safe reinforcement learning with stability guarantees☆222Updated 2 years ago
- Safe Exploration with MPC and Gaussian process models☆87Updated 4 years ago
- ☆236Updated last year
- PILCO policy search framework (Matlab version)☆63Updated 6 years ago
- Learning Lyapunov functions and control policies of nonlinear dynamical systems☆117Updated 3 years ago
- Safe exploration in Markov Decision Processes☆38Updated 6 years ago
- A toolbox for trajectory optimization of dynamical systems☆50Updated 2 years ago
- The reimplementation of Model Predictive Path Integral (MPPI) from the paper "Information Theoretic MPC for Model-Based Reinforcement Lea…☆88Updated 4 years ago
- Working directory for dynamics learning for experimental robots.☆55Updated 3 years ago
- Synthesizing neural-network Lyapunov functions (and controllers) as stability certificate.☆138Updated 8 months ago
- Bayesian Reinforcement Learning in Tensorflow☆312Updated 3 years ago
- Differential Dynamic Programming controller operating in OpenAI Gym environment.☆86Updated 4 years ago
- Implementation of robust adaptive control methods for the linear quadratic regulator☆36Updated 2 years ago
- Source code for the examples accompanying the paper "Learning convex optimization control policies."☆80Updated last year
- Implementation of a differetiable discrete-time algebraic Riccati equation (DARE) solver in PyTorch.☆11Updated last year
- A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, contr…☆158Updated 11 months ago
- ☆60Updated 6 months ago
- Enforcing robust control guarantees within neural network policies