RL without TD learning
- TD: 3 events in the last 90 days
What happened
In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalability challenges ), and scales well to long-horizon tasks. We can do Reinforcement Learning (RL) based on divide and conquer, instead of temporal difference (TD) learning. Problem set…
Summary assembled by rule from the sources below
Why it's spreading
- ConfirmedBAIR Blog published a first-party announcement
Timeline
- First appeared on BAIR BlogBAIR Blog
Sources
Official
- RL without TD learningBAIR Blog