Max Schwarzer
TalkRL: The Reinforcement Learning Podcast
BBF: A Collection of Improvements on Top of DQN
BBF is the latest in a long line of work built on top of Rainbow DQN that was the 2017 agent, descended from the original DQN or deep Q network. Is BBF similar in that it's a collection of improvements on top of the previous generation? I think that's a good way of looking at it. Absolutely. From DQN, Rainbow, as you mentioned, the collection of published improvements that seemed to be important during between those times.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
