Fusion-ML

trajectory-information-rl

Bayesian active RL (BARL) and trajectory information planning (TIP)

OCBO

Offline Contextual Bayesian Optimization

bac-baselines

A variety of baselines and experiment code for the Bayesian active control project

calibrated_uncertainty

plasma-profile-predictor

gym-http-api

API to access OpenAI Gym from other languages via HTTP

handful-of-trials

Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

ocbo_qlearning

rlkit

Collection of reinforcement learning algorithms

torchdiffeq

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.