ischubert Goto Github PK

bpy-scripting

Blender python bpy scripts

code

ddpg

Reinforcement learning in python using DDPG (Lillicrap et al. 2016)

fv-rs

Code base for reproducing results of ICLR 2021 paper "Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks"

gym-obstacles

OpenAI-Gym obstacle avoidance environment for training plan-conditioned policies

gym-physx

OpenAI-Gym Robotics Manipulation Environment. Based on PhysX Simulator / with KOMO planning

l2e

Code base for reproducing results of I.Schubert, D.Driess, O.Oguz, and M.Toussaint: Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics. NeurIPS (2021)

lazyq

Q-learning with lazy action model in Python. Workshop paper for MLPC@ICRA 2020.

pytorch_sac

PyTorch implementation of Soft Actor-Critic (SAC)

rai

Robotic AI bare code. This is designed as shared submodule of other projects. Try other repos that expose just one functionality (KOMO, LGP) first.

rai-python

Python bindings to rai. Simple interface to work with robot/world configurations, compute features and their Jacobians, inverse kinematics, path optimization.

rai-robotmodels

Model files for Baxter, PR2, Kuka arm, and other

risk_assessment

Estimating the risk of an investment dependening on the duration using historic stock value data.

ryenv

Example environments for Reinforcement Learning with ry

stable-baselines3

stable-baselines3-1

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.