MinRegret / deluca
Performant, differentiable reinforcement learning
☆25Updated last year
Related projects: ⓘ
- Google AI Princeton control framework☆38Updated 3 years ago
- ☆30Updated 10 months ago
- ☆33Updated last year
- ☆27Updated 3 years ago
- Model-based reinforcement learning (generative simulator models and planning agents)☆15Updated 3 years ago
- JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"☆43Updated 3 years ago
- A toolbox for inference of switching systems for control☆13Updated 3 years ago
- Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (NeurIPS2021)☆20Updated 2 years ago
- ☆26Updated 5 years ago
- ☆32Updated last year
- a modular reinforcement learning library with JAX agents☆20Updated 10 months ago
- On the model-based stochastic value gradient for continuous reinforcement learning☆54Updated last year
- Code for reproducing experiments in Model-Based Active Exploration, ICML 2019☆77Updated 5 years ago
- Model-based reinforcement learning in TensorFlow☆53Updated 3 years ago
- Standalone library of frequently-used wrappers for dm_env environments.☆18Updated 2 months ago
- ☆27Updated 3 years ago
- ☆33Updated 4 years ago
- Repository for the paper "Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors"☆44Updated last year
- Implementation of PILCO for the Model-Based Baselines Project☆17Updated 5 years ago
- Model-Based Reinforcement Learning via Latent-Space Collocation.☆31Updated last year
- Code for the PAC-Bayes Control paper.☆13Updated last year
- improved Cross Entropy Method for trajectory optimization☆65Updated 3 years ago
- Python bindings to some optimization benchmarks (robotics problems), in order to constrained optimization solvers. Includes also an inter…☆20Updated last year
- Trajectory optimization algorithms for robotic control.☆101Updated last year
- Source code for the paper "Policy Architectures for Compositional Generalization in Control"☆29Updated 2 years ago
- Myriad is a real-world testbed that aims to bridge trajectory optimization and deep learning.☆58Updated last year
- The code accompaniment for the CoRL 2020 paper: A User's Guide to Calibrating Robotics Simulators (https://arxiv.org/abs/2011.08985), fro…☆29Updated 3 years ago
- Input Inference for Control (i2c), a control-as-inference framework for optimal control☆23Updated last year
- reinforcement learning from randomized simulations☆64Updated this week
- My Body Is A Cage☆37Updated 3 years ago