diff --git a/crates/ml-alpha/src/trainer/integrated.rs b/crates/ml-alpha/src/trainer/integrated.rs index 74724f12a..9b8cedcf3 100644 --- a/crates/ml-alpha/src/trainer/integrated.rs +++ b/crates/ml-alpha/src/trainer/integrated.rs @@ -2768,8 +2768,8 @@ impl IntegratedTrainer { (crate::rl::isv_slots::RL_TARGET_TAU_MAX_INDEX, 0.005), (crate::rl::isv_slots::RL_HOLD_PRIOR_INDEX, 0.1), (crate::rl::isv_slots::RL_HOLD_TARGET_FRAC_INDEX, 0.5), - (crate::rl::isv_slots::RL_KL_REF_BETA_INDEX, 0.003), - (crate::rl::isv_slots::RL_REWARD_KL_BETA_INDEX, 0.005), + (crate::rl::isv_slots::RL_KL_REF_BETA_INDEX, 0.0005), + (crate::rl::isv_slots::RL_REWARD_KL_BETA_INDEX, 0.001), (crate::rl::isv_slots::RL_KL_REF_TARGET_INDEX, 0.5), (crate::rl::isv_slots::RL_EPS_BOOTSTRAP_INDEX, 0.2), (crate::rl::isv_slots::RL_ROLLOUT_BOOTSTRAP_INDEX, 2048.0),