Evolving Reinforcement Learning Algorithms

A new method for meta-learning RL algos by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. Read the full paper at: https://arxiv.org/pdf/2101.03958.pdf

13Upvotes
thumb_upthumb_downchat_bubble

More from AzDeck

The Solar System

111 views · May 4th
repeat
233 views

☁️Cloudy path☁️

233 views · May 3rd

More from AzDeck

The Solar System

111 views · May 4th
repeat
233 views

☁️Cloudy path☁️

233 views · May 3rd