Tag: 강화학습
-
Sim-to-Real Transfer 완전 가이드: 시뮬레이션 강화학습을 실제 로봇에 적용하는 방법
Sim-to-Real transfer: train robot policies 100x faster in simulation, deploy to hardware with 85% success rate. Domain randomization code.
-
MARL 실전 가이드: QMIX, MAPPO, MADDPG 구현 비교
QMIX vs MAPPO vs MADDPG on cooperative tasks: which multi-agent RL algorithm converges faster? Benchmarks from 10M training steps.
-
Offline RL 정복: CQL, IQL, Decision Transformer 비교
Offline RL showdown: CQL vs IQL vs Decision Transformer on D4RL benchmarks. Train agents without environment interaction.
-
RLHF로 언어모델 정렬하기: ChatGPT부터 Claude까지의 실전 구현 가이드
RLHF implementation guide: train ChatGPT-style models with human feedback. PPO + reward model code walkthrough included.