diff --git a/crates/ml-alpha/src/trainer/integrated.rs b/crates/ml-alpha/src/trainer/integrated.rs index 831e1365e..003420968 100644 --- a/crates/ml-alpha/src/trainer/integrated.rs +++ b/crates/ml-alpha/src/trainer/integrated.rs @@ -2686,8 +2686,8 @@ impl IntegratedTrainer { // outliers." V_MAX/V_MIN seeded to the original C51 // [-1, +1] span as the canonical floor — the ratchet // in `rl_reward_clamp_controller` only grows magnitude. - (crate::rl::isv_slots::RL_REWARD_CLAMP_WIN_INDEX, 0.5), - (crate::rl::isv_slots::RL_REWARD_CLAMP_LOSS_INDEX, 0.5), + (crate::rl::isv_slots::RL_REWARD_CLAMP_WIN_INDEX, 1.0), + (crate::rl::isv_slots::RL_REWARD_CLAMP_LOSS_INDEX, 3.0), (crate::rl::isv_slots::RL_REWARD_CLAMP_MARGIN_INDEX, 1.5), (crate::rl::isv_slots::RL_REWARD_CLAMP_RATIO_INDEX, 3.0), (crate::rl::isv_slots::RL_REWARD_CLAMP_CLIP_RATE_TARGET_INDEX, 0.05),