Coarse Coding, such as Tile Coding, is a nice way of storing a model of the environment linear in nature or have ordinal characteristics (for instance, alphabets are ordinal since it can be ordered: A < B < C, …). The image above illustrates how Coarse Coding may be utilized. a) Narrow Generalization is for … Read more
With my Sparse Distributed Memory (SDM) basic implementation finally done, in which the Up/Down Counters won’t overflow, I’m ready to embark something bigger. At the moment, my implementation stores everything in random-access-memory (RAM), which is very limiting. I have utilized SDM with my reinforcement learning (rl), solving entailments in a set of 11,000 metrics, which … Read more
Sparse Distributed Memory (SDM) is a fascinating way of managing the exponential growth in memory. As opposed to the traditional random-access memory (RAM) where there is a one to one correspondence between an address and a hard location, SDM can map multiple addresses to a multiple of hard location. I won’t delve into why this … Read more