Field dossier · from the corpus
Reinforcement
0predicted collisions
Where this field is predicted to collide
No open collisions on this field in the current run.
Most cited work
Neural Architecture Search with Reinforcement Learning
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Sigmoid-weighted linear units for neural network function approximation in reinforcement learning
10. Reinforcement learning
Rainbow: Combining Improvements in Deep Reinforcement Learning
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Recent work · 2024 onward