RLHF

PoEM: Predicting RL Outcomes Without Re-training Existing Policies

不需重新訓練！PoEM 演算法直接預測新獎勵函數的強化學習結果

The PoEM framework enables researchers to accurately predict and synthesize new RL policies without any actual RL training, by leveraging linear combinations of existing post-trained models in log-space.