RL Grind

7.30.2025 -

Learned for: 6 hours

Finished up a couple videos on GRPO today, gonna set up sessions on Spaced to cover this paper. Also watched half of a David Silver lecture, I need to reintroduce the fundamentals that elude me. I got stuck reading manhwa for a long time, even if it was very compelling there can be no excuse. I am not here because I want to have a lot of fun. I want to work hard, suffer even, to find greatness within the field of RL.

8.1.2025 -

Learned for: 4 hours

Played a bunch of clash royale this morning instead of learning, it will not happen again. I also finished up the policy gradient lecture, so tomorrow I will watch another and find exercises from the textbook to do to boost understanding.

8.3.2025 -

Learned for: 4 hours

I think I missed yesterday. Anyways yeah I kinda did something similar to the day before, but I’m bouncing back now. Working hard to get my own RL library set up. I can tell that it will be extremely informative to how RL gets programmed. Taking it slow and steady, not skipping on anything or letting AI take the wheel. I will be deliberate and comprehensive to not just look like I know what I’m doing, but actually be able to back it up.

8.14.2025 -

Learned for: a lot of hours

Honestly I’m just gonna port here when I feel like it for rn. I’m working on the experiment space for RL stuff, and it is time to grind out job apps until something sticks. I’m gonna make a big ol plan and spreadsheet for scheduling applying. Also want to do the same thing with instagram, want to try my hand at some content creation potentially. Finally, really trying to get into an AI lab next semester, I think that would be awesome.