pedronahum Goto Github PK

agents

Efficient Batched Reinforcement Learning in TensorFlow

ai-economist

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

arcade-learning-environment

The Arcade Learning Environment (ALE) -- a platform for AI research.

arrayfire

ArrayFire: a general purpose GPU library.

ars

An implementation of the Augmented Random Search algorithm for The DeepMind Control Suite and Package

big

CMU RI BIG

binarynet.pytorch

Binarized Neural Network (BNN) for pytorch

bullet3

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

bwapi

Brood War API

category-theory-for-dotnet-programmers

This repo contains all c++ / haskell samples from Bartosz Milewski's book (Category Theory for Programmers) converted to csharp and fsharp

chapelvscode

Chapel support for Visual Studio Code

chatzilygeroudis_2018_rte

Code for the Reset-free Trial and Error learning paper (RTE) experiments

conservative-uncertainty-estimation-random-priors

Source code for paper Conservative Uncertainty Estimation By Fitting Prior Networks (ICLR 2020)

cql

Code for conservative Q-learning

dan

A new architecture of semantic segmentation called Dense-Attention Networks.

dart

diffkt

A framework for automatic differentiation in Kotlin

dm-control-rl

Implementations of reinforcement learning algorithms on top of The DeepMind Control Suite and Package

dm_control

The DeepMind Control Suite and Package

fsi-samples

A collection of open-source GPU accelerated Python tools and examples for quantitative analyst tasks and leverages RAPIDS AI project, Numba, cuDF, and Dask.

ga3c

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

google-research

Google Research

hanabi_sad

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

hanabi_sparta

Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it

ite_v2

Intelligent Trial & Error Algorithm for Robot Adaptation

learn_solana

naiad

The Naiad system provides fast incremental and iterative computation for data-parallel workloads

noiseinjection

Fork of DART: Noise Injection for Imitation Learning

noreward-rl

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.