Neural Network Architectures
Julian and Tim discuss the challenges of reinforcement learning and symbolic methods in neural network architectures. They explore the limitations of single-objective training and the benefits of multi-objective systems in tackling complex environments like the Nethack challenge.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#81 JULIAN TOGELIUS, Prof. KEN STANLEY - AGI, Games, Diversity & Creativity [UNPLUGGED]
Related Questions
How does symbolic reasoning compare to neural networks?
What is symbolic reasoning in the context of the episode "Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15" and the clip "Knowledge Representation Challenges"?
What is symbolic reasoning as discussed in the episode Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15 and the clip Knowledge Representation Challenges?