SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inferen...
Reinforcement learning with unsupervised auxiliary tasks
The Tensorflow code and a DeepMind Lab wrapper for my article "Meta-Rein...
A Test-Implementation of the IMPALA algorithm (by deepmind 2018)
Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum f...