deepmind-lab

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

Reinforcement learning with unsupervised auxiliary tasks

Tensorflow implementation of DeepMind paper - "Learning to Navigate in Complex Environments"

The Tensorflow code and a DeepMind Lab wrapper for my article "Meta-Reinforcement Learning" on FloydHub.

A Test-Implementation of the IMPALA algorithm (by deepmind 2018)

Reinforcement learning in 3D.

PyTorch implementation of two variants of the Harlow visual fixation task (PsychLab and 1D version). Reproduces the results found in two papers. Check the ReadMe for more details!

CS 238 Final Project: Deep Reinforcement Learning Agents that Run with Scissors

A customizable 3D platform for agent-based AI research

Deepmind lab gym-like wrapper

Using deepmind lab for RL

Docker hub for easily setting up reinforcement learning research environment