I was inspired by this post by Matheus_Araujo on playing rock paper scissors against HTM. I thought to my self that why not let HTM play again a RNN or even a LSTM network? And so it becomes a side project of mine. Framing the problem The ides is to have 2 agents, one implement in RNN and one in …

HTM vs GRU playing Rock, Paper, Scissors. (HTM outperforming by 7%)

marty1885 December 18, 2018, 4:08pm 14

I turned off learning in HTM after 20K games. ( RNN still learns after that point)
htm_win_rate

3 Likes

Playing Rock, Paper, Scissors with HTM, Take 2

Topic		Replies	Views
Playing Rock, Paper, Scissors with HTM, Take 2 Applications sequence-memory	19	1313	October 9, 2019
An open-source community research project on comparing HTM-RL to conventional RL Related Papers	63	3343	June 19, 2018
RNNs and HTM Machine Learning community	18	1329	January 10, 2019
Exciting potentials with HTM agents in OpenAI Gym Engineering	5	539	October 20, 2019
Reinforcement Learning and HTM Algorithm Machine Learning sequence-memory , encoders , question , community , nupic	26	3552	June 18, 2019