bthananjeyan / saved-rl
Implementation of safety augmented value estimation from demonstrations (SAVED)
☆22Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for saved-rl
- Model Predictive Actor-Critic Reinforcement Learning☆52Updated 3 years ago
- Cross Entropy Method implemented in pytorch☆36Updated 2 years ago
- ☆25Updated 3 years ago
- Code needed to reproduce the examples found in "Learning Control Barrier Functions from Expert Demonstrations," by A. Robey, H. Hu, L. Li…☆57Updated last year
- Code accompanying the paper: "Stable Motion Primitives via Imitation and Contrastive Learning" (T-RO).☆22Updated last year
- An MPC algorithm which supports polytopic state and action constraints, using CEM optimisation.☆13Updated 5 years ago
- Working directory for dynamics learning for experimental robots.☆56Updated 3 years ago
- Formulating Model-based RL Dynamics as a continuous rather then one step prediction☆35Updated 2 years ago
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆62Updated last year
- Robot Reinforcement Learning on the Constraint Manifold☆47Updated 2 years ago
- The reimplementation of Model Predictive Path Integral (MPPI) from the paper "Information Theoretic MPC for Model-Based Reinforcement Lea…☆90Updated 4 years ago
- Trajectory optimization algorithms for robotic control.☆101Updated 2 years ago
- Sampling based Model Predictive Control package for Model-Based RL research☆51Updated 4 years ago
- Implementation of robust adaptive control methods for the linear quadratic regulator☆36Updated 2 years ago
- Guided policy search in Python and ROS Indigo.☆24Updated 6 years ago
- Implemented Guided Policy Search algorithm using the V-REP Simulator for 1) 7-DOF robotic arm, 2) quadcopter.☆8Updated 7 years ago
- Implementation of an iterative linear quadratic regular (iLQR) on inverted pendulum, box quadratic programming (box-QP) is used to deal w…☆10Updated 6 years ago
- Implementation of Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.☆52Updated last year
- Implementation of PILCO for the Model-Based Baselines Project