rcurtin_irc changed the topic of #mlpack to: mlpack: a scalable machine learning library (https://www.mlpack.org/) -- channel logs: https://libera.irclog.whitequark.org/mlpack -- NOTE: messages sent here might not be seen by bridged users on matrix, gitter, or slack
<TriWahyuGuntara[> <zoq[m]> "> <@marcusedel:matrix.org> Hello..." <- I see. What do you think about implementing DDPG and TD3, and fix SAC for GSoC this year?
<TriWahyuGuntara[> To the best of my knowledge, upon reading the SAC implementation, the implemented SAC actually resembles TD3 more than SAC. It uses deterministic policy and no entropy term for actor objective. It just needs delayed policy update to turn current SAC implementation into TD3. Perhaps you have other suggestions for RL GSoC this year?
kevin94 has joined #mlpack
lambert[m] has joined #mlpack
kevin94 has quit [Quit: Client closed]
Guest1 has joined #mlpack
Guest1 has quit [Client Quit]
<zoq[m]> > <@gunnxx:gitter.im> I see. What do you think about implementing DDPG and TD3, and fix SAC for GSoC this year?
<zoq[m]> >
<zoq[m]> > To the best of my knowledge, upon reading the SAC implementation, the implemented SAC actually resembles TD3 more than SAC. It uses deterministic policy and no entropy term for actor objective. It just needs delayed policy update to turn current SAC implementation into TD3. Perhaps you have other suggestions for RL GSoC this year?
<zoq[m]> I like the ideas, personally I would probably remove DDPG from the list, or mention to implement if you have time left at the end.
UtkarshMathur[m] has joined #mlpack
SuneethJerri[m] has joined #mlpack
<aadi-rajAdityaRa> zoq
<aadi-rajAdityaRa> zoq: rcurtin Hey, I am Aditya Raj. I have done little bit of research on deep RL. I am thinking of implementing ACKTR and multistep reinforcement learning as GSoC project this year. What do you think about the ideas?
<zoq[m]> <aadi-rajAdityaRa> "zoq: rcurtin Hey, I am Aditya..." <- I like the idea, ACKTR in particular.
<zoq[m]> > <@_slack_mlpack_U04UZS0B610:matrix.org> Hi mlpack team,... (full message at <https://libera.ems.host/_matrix/media/v3/download/libera.chat/4dceaf9c95d381dab867aa0d06636eaa4286665a>)
<zoq[m]> zoq[m]: Also, reviews on open patches are always welcome as well.
Axiomatik has quit [Ping timeout: 276 seconds]
lxi has joined #mlpack
Aryaman123_Fauzd has joined #mlpack
<Aryaman123_Fauzd> Hello everyone! Myself, Aryaman Singh Fauzdar, a 3rd-year undergrad student pursuing Bachelor of Technology in Computer Science and Engineering from Manipal University Jaipur in India. I went through the list of project ideas for GSOC 2023 on the GitHub page of MLPack and found the project idea "Visualization... (full message at <https://libera.ems.host/_matrix/media/v3/download/libera.chat/7dc7d24a20163455c7d25ddee0741bf1857d8a85>)
<Aryaman123_Fauzd> * Hello everyone! Myself, Aryaman Singh Fauzdar, a 3rd-year undergrad student pursuing Bachelor of Technology in Computer Science and Engineering from Manipal University Jaipur in India. I went through the list of project ideas for GSOC 2023 on the GitHub page of MLPack and found the project idea "... (full message at <https://libera.ems.host/_matrix/media/v3/download/libera.chat/24091defd850d9ec1cf64b6203e1f7220cfd4d5b>)
<Aryaman123_Fauzd> * Hello everyone! Myself, Aryaman Singh Fauzdar, a 3rd-year undergrad student pursuing Bachelor of Technology in Computer Science and Engineering from Manipal University Jaipur in India. I went through the list of project ideas for GSOC 2023 on the GitHub page of MLPack and found the project idea "... (full message at <https://libera.ems.host/_matrix/media/v3/download/libera.chat/1701afd68c57035c2c6a02c339c64c93e2bb3bcf>)