# Retrospective Likelihood-based Action Credit Assignment

RELACE is a critic-free framework that uses a frozen behavior policy to teacher-force score each executed action under both its original context and an outcome-augmented context, normalizes and clips the ratio of these length-normalized scores within each trajectory to reweight discounted returns, and then builds local advantages by comparing weighted returns among actions from matched states, combining them with trajectory-level GRPO supervision; on ALFWorld and WebShop with Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct it reports the highest mean aggregate metrics among the compared methods, including GRPO, GiGPO, HCAPO, and GraphGPO.

RELACE is a critic-free framework that uses a frozen behavior policy to teacher-force score each executed action under both its original context and an outcome-augmented context, normalizes and clips the ratio of these length-normalized scores within each trajectory to reweight discounted returns, and then builds local advantages by comparing weighted returns among actions from matched states, combining them with trajectory-level GRPO supervision; on ALFWorld and WebShop with Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct it reports the highest mean aggregate metrics among the compared methods, including GRPO, GiGPO, HCAPO, and GraphGPO.