The M Tank's repositories
RL-code-resources
A collection of Reinforcement Learning GitHub code resources divided by frameworks and environments
cups-rl
Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"
GridUniverse
Old and new Reinforcement Learning algorithms run on the GridUniverse ecosystem
ai-distillery
Automatically modelling and distilling knowledge within AI. In other words, summarising the AI research firehose.
ai-distillery-app
This website will hold our dynamic content e.g. search proximal words from embeddings and visualizing them
mega-distance-speed-tests
Speed comparisons between many different euclidean and cosine metrics across many different libraries
word2vec-explorer
Tool for exploring Word Vector models
anki-vector
Environment wrapper to control Vector robot from Anki
arxiv-sanity-preserver
Web interface for browsing, search and filtering recent arxiv submissions
rl_course_resources
Scripts for running examples for the reinforcement learning course
themtank.github.io
The M Tank's blogging website