-
-
-
NeuralSlime Public
An experimental artificial life sim where each cell is controlled by a neural network and weights diffuse with organic matter.
Python MIT License UpdatedJun 18, 2023 dreamerv2_JAX Public
An implementation of DreamerV2 written in JAX, with support for running multiple random seeds of an experiment on a single GPU.
Code for "The Benefits of Model-Based Generalization in Reinforcement Learning"
dreamerv2 Public
An implementation of DreamerV2 written in JAX and Haiku.
multiwandb Public
Simple way to run multiple wandb instances in a single script.
Python MIT License UpdatedNov 25, 2022 HNCA_code_supplement Public
Code Supplement for the Paper: "Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units"
Python MIT License UpdatedDec 13, 2021 gym Public
Forked from openai/gymA toolkit for developing and comparing reinforcement learning algorithms.
Python Other UpdatedNov 4, 2021 playground Public
Forked from MultiAgentLearning/playgroundPlayGround: AI Research into Multi-Agent Learning.
ai-deadlines Public
Forked from paperswithcode/ai-deadlines⏰ AI conference deadline countdowns
HTML UpdatedOct 4, 2017 lab Public
Forked from google-deepmind/labA customisable 3D platform for agent-based AI research
C Other UpdatedDec 7, 2016 PansophyBot Public
Forked from Pansophy350/PansophyBotA customized AI system for StarCraft Brood War based on UalbertaBot
C++ UpdatedDec 3, 2015 morat Public
Forked from tewalds/moratA program to play Gomoku, Havannah, Hex, Rex, Y and Pentago.
C++ MIT License UpdatedMay 20, 2015
{{ message }}