paper-with-me

홈 › Papers

Causally Correct Partial Models for Reinforcement Learning

2020-02-07 · Danilo J. Rezende, Ivo Danihelka, George Papamakarios, Nan Rosemary Ke, Ray Jiang, Theophane Weber, Karol Gregor, Hamza Merzic, Fabio Viola, Jane Wang, Jovana Mitrovic, Frederic Besse, Ioannis Antonoglou, Lars Buesing

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the observations are high-dimensional (e.g. images). For this reason, previous works have considered partial models, which model only part of the observation. In this paper, we show that partial models can be causally incorrect: they are confounded by the observations they don't model, and can therefore lead to incorrect planning. To address this, we introduce a general family of partial models that are provably causally correct, yet remain fast because they do not need to fully model future observations.

📄 PDF Abstract BibTeX arXiv:2002.02836

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Causally-Enhanced Reinforcement Policy Optimization

2025-09-27 · Xiangqi Wang, Yue Huang, Yujun Zhou, Xiaonan Luo 외 arxiv

Large language models (LLMs) trained with reinforcement objectives often achieve superficially correct answers via shortcut strategies, pairing correct outputs with spurious or unfaithful reasoning and degrading under sm…

Identification of Partially Observed Linear Causal Models: Graphical Conditions for the Non-Gaussian and Heterogeneous Cases

2021-12-01 · NeurIPS 2021 12 · Jeffrey Adams, Niels Hansen, Kun Zhang

In causal discovery, linear non-Gaussian acyclic models (LiNGAMs) have been studied extensively. While the causally sufficient case is well understood, in many real problems the observed variables are not causally relate…

Causal Discovery

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

2025-10-23 · Dian Yu, Yulai Zhao, Kishan Panaganti, Linfeng Song 외 arxiv

We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. While Reinforcement Learning with Verifiab…

Reinforcement Learning

CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments

2023-04-13 · Ricardo Cannizzaro, Lars Kunze

Robots operating in real-world environments must reason about possible outcomes of stochastic actions and make decisions based on partial observations of the true world state. A major challenge for making accurate and ro…

Decision Making

Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation

2026-01-07 · Longwen Wang, Yirui Liu, Xuan'er Wu, Xiaohui Hu 외 arxiv

Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but induce sparsity, while external Reward Mod…

Reinforcement LearningCode Generation