paper-with-me

홈 › Papers

Policy Learning with a Natural Language Action Space: A Causal Approach

2025-02-24 · Bohan Zhang, Yixin Wang, Paramveer S. Dhillon

This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While recent approaches like Proximal Policy Optimization (PPO) can handle such delayed-reward settings in high-dimensional action spaces, they typically require multiple models (policy, value, and reward) and substantial training data. Our approach employs Q-learning to estimate Dynamic Treatment Regimes (DTR) through a single model, enabling data-efficient policy learning via gradient ascent on language embeddings. A key technical contribution of our approach is a decoding strategy that translates optimized embeddings back into coherent natural language. We evaluate our approach on mental health intervention, hate speech countering, and sentiment transfer tasks, demonstrating significant improvements over competitive baselines across multiple metrics. Notably, our method achieves superior transfer strength while maintaining content preservation and fluency, as validated through human evaluation. Our work provides a practical foundation for learning optimal policies in complex language tasks where training data is limited.

📄 PDF Abstract BibTeX arXiv:2502.17538

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingQ-Learning

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

LangMARL: Natural Language Multi-Agent Reinforcement Learning

2026-04-01 · Huaiyuan Yao, Longchao Da, Xiaoou Liu, Charles Fleming 외 arxiv

Large language model (LLM) agents struggle to autonomously evolve coordination strategies in dynamic environments, largely because coarse global outcomes obscure the causal signals needed for local policy refinement. We …

Multi-agent Reinforcement Learning

Towards a Grounded Theory of Causation for Embodied AI

2022-06-28 · Taco Cohen

There exist well-developed frameworks for causal modelling, but these require rather a lot of human domain expertise to define causal variables and perform interventions. In order to enable autonomous agents to learn abs…

Group Causal Policy Optimization for Post-Training Large Language Models

2025-08-07 · Ziyin Gu, Jingyao Wang, Ran Zuo, Chuxiong Sun 외 arxiv

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimiz…

Indexing and Visualization of Climate Change Narratives Using BERT and Causal Extraction

2024-08-03 · Hiroki Sakaji, Noriyasu Kaneda

In this study, we propose a methodology to extract, index, and visualize ``climate change narratives'' (stories about the connection between causal and consequential events related to climate change). We use two natural …

Articles

Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space

2025-12-04 · Joey Hong, Kang Liu, Zhan Ling, Jiecao Chen 외 arxiv

Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-us…