Do computers learn using positive reinforcement or negative reinforcement?
Nothing feels more like Artificial Intelligence than when a computer learns by itself through repeated simulations. Computers can now master games by simply playing the game over and over against itself. This is reinforcement learning. Today we have David Stroud on the show to explain to us a bit of reinforcement learning. He’ll give us the base needed when hearing and understanding Reinforcement Learning. David Stroud is a Reinforcement Learning Researcher and Lecturer of Information Systems and Quantitative Methods at Troy University. You can find more information about Reinforcement Learning and links to other resources on David’s Github page below: https://github.com/RL-Research-Cohiba/Reinforcement_Learning After listening to the episode, do you think computers learning using positive or negative reinforcement? We want to hear your thoughts.