psclklnk

keops

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

crocoddyl

Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

boosted_crl

currot

Source Code for the ICML Paper "Curriculum Reinforcement Learning via Constrained Optimal Transport"

optimal-transport-curricula

Code accompanying the T-PAMI paper "On the Benefit of Optimal Transport for Curriculum Reinforcement Learning"

pspl-code

Source Code: A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning

self-paced-rl

Implementation of the Self Paced Reinforcement Learning Experiments

spdl

Source code for the Self-Paced Deep Reinforcement Learning Experiments

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

psclklnk/spdl

Source code for the Self-Paced Deep Reinforcement Learning Experiments

psclklnk/self-paced-rl

Implementation of the Self Paced Reinforcement Learning Experiments

psclklnk/currot

Source Code for the ICML Paper "Curriculum Reinforcement Learning via Constrained Optimal Transport"

psclklnk/boosted_crl

psclklnk/optimal-transport-curricula

Code accompanying the T-PAMI paper "On the Benefit of Optimal Transport for Curriculum Reinforcement Learning"

psclklnk/pspl-code

Source Code: A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning