Gregory Palmer's repositories
nui_in_madrl
Negative Update Intervals in Multi-Agent Deep Reinforcement Learning
CycleGAN-tensorflow
Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf
deep-rl-tensorflow
TensorFlow implementation of Deep Reinforcement Learning papers
gjp1203.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
gym
A toolkit for developing and comparing reinforcement learning algorithms.
mujoco-py
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Orion
A machine learning library for detecting anomalies in signals.
plark_ai_public
Montvieux has developed “The hunting of the PLARK” Artificial Intelligence (AI) testbed to support a Hackathon activity at the Alan Turing Institute (ATI). The testbed is very flexible and will support both short term exercises in the Hackathon and provide a basis for more extensive, long-term, and cutting edge research. The test bed can be used as a basis to research the limits of agent generalisation, co-operation, and deception in a defence environment.
rl_tournament
Reinforcement Learning Tournament Director
tensorflow
An Open Source Machine Learning Framework for Everyone