paper-with-me

홈 › Papers

From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction

2018-04-29 · ACL 2018 7 · Zihang Dai, Qizhe Xie, Eduard Hovy

In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counterpart of RAML and the entropy regularized reinforcement learning. Inspired by the connection, we propose two sequence prediction algorithms, one extending RAML with fine-grained credit assignment and the other improving Actor-Critic with a systematic entropy regularization. On two benchmark datasets, we show the proposed algorithms outperform RAML and Actor-Critic respectively, providing new alternatives to sequence prediction.

📄 PDF Abstract BibTeX arXiv:1804.10974

Code (1)

zihangdai/ERAC-VAML 공식 구현 pytorch

Tasks

Predictionreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy Regularization

2022-02-09 · Jian Zhao, Yue Zhang, Xunhan Hu, Weixun Wang 외

In cooperative multi-agent systems, agents jointly take actions and receive a team reward instead of individual rewards. In the absence of individual reward signals, credit assignment mechanisms are usually introduced to…

Guided Adaptive Credit Assignment for Sample Efficient Policy Optimization

2019-09-25 · Hao liu, Richard Socher, Caiming Xiong

Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from sparse reward tasks, which leads to poor sample efficiency during tr…

Instruction FollowingPolicy Gradient Methods

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy

2025-08-06 · Hongze Tan, Zihan Wang, Jianfei Pan, Jinghao Lin 외 arxiv

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all toke…

Reinforcement Learning

Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR

2026-05-07 · Chaoli Mou, Zhan Zhuang, Xinning Chen, Yu Zhang arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. However, widely used critic-free algorithms such as Group Relative Policy Op…

Reinforcement Learning

Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning

2020-07-06 · NeurIPS 2020 12 · Meng Zhou, Ziyu Liu, Pengwei Sui, Yixuan Li 외

We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings. Our key motivation is that credit assignment among agents may not require an ex…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1