lagrassa Goto Github PK

actionlib

Provides a standardized interface for interfacing with preemptable tasks. Examples of this include moving the base to a target location, performing a laser scan and returning the resulting point cloud, detecting the handle of a door, etc.

apriltags-cpp

AprilTags C++ library

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

bugsy

clippy-for-vim

cma-agent

Train RL agents with CMA-ES

cmax

Planning and Execution using Inaccurate Models with Provable Guarantees

cmu-ai-mentoring

dmp

This ROS package is a general, robot-agnostic implementation of dynamic movement primitives (DMPs).

due

Code for "On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty".

excelclass

High school class for ESP

freedomsquares

granular-planning

gym

A toolkit for developing and comparing reinforcement learning algorithms.

handful-of-trials

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

hindsight-experience-reinterpretation

Joke repository

image-recolorization

intro-search-lab

keras-rl

Deep Reinforcement Learning for Keras.

lagrassa.github.io

Personal website

learn_prim_skills

liquid_light

A way to control a liquid light display based on the volumes of inputted sounds.

mdp-toolkit

MDP code

mentorship-matching

Algorithm for running mentoring program matching algorithm

model-preconditions

Code accompanying the paper "Learning Model Preconditions for Planning with Multiple Models"

models

Models and examples built with TensorFlow

mpc_mdp

solving markov decision processes model predictive control

music21

music21 is a Toolkit for Computational Musicology

music21j

Javascript port of music21 -- Toolkit for Computational Musicology

naf-tensorflow

"Continuous Deep Q-Learning with Model-based Acceleration" in TensorFlow