Meta Policy Gradient
Tom discusses the essence of meta learning in reinforcement algorithms, emphasizing the adaptation to specific environments for improved learning. He delves into the evolution of metagradients, from hyperparameters to intrinsic rewards, shedding light on the distinctions between white box and black box methods.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#49 - Meta-Gradients in RL - Dr. Tom Zahavy (DeepMind)
Related Questions