kchua/handful-of-trials
Experiment code for PETS, a model-based deep reinforcement learning algorithm using probabilistic neural network dynamics models.
Not currently ranked — collecting fresh signals.
star history
This repository implements the PETS (Probabilistic Ensembles with Trajectory Sampling) algorithm from a 2018 paper, combining uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation for reinforcement learning. The code trains RL agents on MuJoCo robotics tasks including CartPole, Reacher, Pusher, and HalfCheetah, achieving model-free-level performance with significantly fewer samples than model-free baselines like SAC and PPO.
Frequently asked
- What is kchua/handful-of-trials?
- Experiment code for PETS, a model-based deep reinforcement learning algorithm using probabilistic neural network dynamics models.
- Is handful-of-trials open source?
- Yes — kchua/handful-of-trials is open source, released under the MIT license.
- What language is handful-of-trials written in?
- kchua/handful-of-trials is primarily written in Python.
- How popular is handful-of-trials?
- kchua/handful-of-trials has 475 stars on GitHub.
- Where can I find handful-of-trials?
- kchua/handful-of-trials is on GitHub at https://github.com/kchua/handful-of-trials.