daniel 🇵🇸
daniel 🇵🇸 @shoogaza ·
#rl fourth time lucky? it’s a 7.5/10 rn but it’s a while since i’ve relistened
356
RustyNeuron
RustyNeuron @rustyneuron_01 ·
🎓 Did some Reinforcement Learning today Used Stable-Baselines3 + custom env. Watched it go from random flailing to actually scoring in under 30 mins. Reward shaping > raw compute. Classic RL still hits different. #ReinforcementLearning #RL #AI #BuildInPublic
8
Kring
Kring @kringrush ·
It’s giving Porto-Broken Social Scene #rl
253