Pdbz199 / koopman-rl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
☆11Updated last month
Alternatives and similar repositories for koopman-rl:
Users that are interested in koopman-rl are comparing it to the libraries listed below
- Use deep learning to learn Koopman operator and LQR for optimal control☆16Updated 4 years ago
- IIB Master's Project: Deep Learning for Koopman Optimal Predictive Control☆45Updated 4 years ago
- We learn the dynamics model of a robot using a physics-informed neural network and use it to train a model-based RL algorithm.☆34Updated 8 months ago
- Pytorch implementation of Model Predictive Control with learned models☆30Updated 4 years ago
- Model-based Control using Koopman Operators☆51Updated 4 years ago
- Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics.☆20Updated last year
- Implementation of Robust Reinforcement Learning using Offline Data [NeurIPS'22]☆23Updated 4 months ago
- Data-driven Koopman control theory applied to reinforcement learning!☆30Updated last year
- Neural Koopman Lyapunov Control☆21Updated last year
- Code for CDC2022 submission☆11Updated last month
- This is a python repo that implements control barrier function quadratic programming method.☆12Updated 3 years ago
- Safety-aware MPC-based RL framework☆54Updated 3 months ago
- An MPC algorithm which supports polytopic state and action constraints, using CEM optimisation.☆14Updated 5 years ago
- PyTorch Implementation of Hamilton-Jacobi DQN☆15Updated 3 years ago
- ☆66Updated 6 years ago
- Neural Lyapunov control of unknown nonlinear systems with stability guarantees☆13Updated last year
- ☆26Updated 3 years ago
- Automatic Tuning for Data-driven Model Predictive Control☆62Updated last year
- Approximate dynamic programming (ADP) and Policy gradient (PG) based sequential optimal experimental design (sOED)☆19Updated 2 years ago
- ☆14Updated last year
- Repository containing the code for the paper "Safe Model-Based Reinforcement Learning using Robust Control Barrier Functions". Specifical…☆43Updated 2 years ago
- This is a Python realization for Milan Korda and Igor Mezic's paper Linear predictors for nonlinear dynamical systems: Koopman operator m…☆10Updated last year
- Python code for implementing a set of basic robust model predictive control (RMPC) algorithms for linear systems.☆25Updated 2 years ago
- Codebase associated with paper "Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control"☆22Updated 4 years ago
- Pytorch version of the MPC in model-based reinforcement learning (MBRL), currently only test in the CartPole-swing-up environment☆80Updated 4 years ago
- Risk-sensitive Inverse Reinforcement Learning☆10Updated 5 years ago
- Learning-Based Efficient Approximation of Data-enabled Predictive Control☆11Updated 11 months ago