English
Related papers

Related papers: Latent Poincar\'e Shaping for Agentic Reinforcemen…

200 papers

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often…

Machine Learning · Computer Science 2022-10-20 Stephen Zhao , Chris Lu , Roger Baker Grosse , Jakob Nicolaus Foerster

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Computation and Language · Computer Science 2025-10-17 Stephen Chung , Wenyu Du , Jie Fu

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…

Machine Learning · Computer Science 2020-07-02 Zijun Zhang , Ruixiang Zhang , Zongpeng Li , Yoshua Bengio , Liam Paull

Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and…

Machine Learning · Computer Science 2026-02-23 Narjes Nourzad , Carlee Joe-Wong

We study reinforcement learning for partially observed Markov decision processes (POMDPs) with infinite observation and state spaces, which remains less investigated theoretically. To this end, we make the first attempt at bridging partial…

Machine Learning · Computer Science 2024-04-02 Qi Cai , Zhuoran Yang , Zhaoran Wang

In this paper, we propose a test-time adaptive agent that performs exploratory inference through posterior-guided belief refinement without relying on gradient-based updates or additional training for LLM agent operating under partial…

Artificial Intelligence · Computer Science 2026-01-01 Seohui Bae , Jeonghye Kim , Youngchul Sung , Woohyung Lim

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Machine Learning · Computer Science 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi

The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. It is theoretically compelling since it can be seen as a Gaussian process posterior with the mean function…

Machine Learning · Computer Science 2023-07-13 Agustinus Kristiadi , Alexander Immer , Runa Eschenhagen , Vincent Fortuin

Latent Dirichlet allocation (LDA) is a widely-used probabilistic topic modeling paradigm, and recently finds many applications in computer vision and computational biology. In this paper, we propose a fast and accurate batch algorithm,…

Machine Learning · Computer Science 2014-04-09 Jia Zeng , Zhi-Qiang Liu , Xiao-Qin Cao

Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language tokens with continuous latent tokens. These methods consume fewer tokens…

Artificial Intelligence · Computer Science 2026-01-30 Zhi Zheng , Wee Sun Lee

Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…

Machine Learning · Computer Science 2021-06-07 Alejandro Daniel Noel , Charel van Hoof , Beren Millidge

The Visual-Language-Action (VLA) models can follow text instructions according to visual observations of the surrounding environment. This ability to map multimodal inputs to actions is derived from the training of the VLA model on…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Jinyue Bian , Zhaoxing Zhang , Zhengyu Liang , Shiwei Zheng , Shengtao Zhang , Rong Shen , Chen Yang , Anzhou Hou

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this…

Computation and Language · Computer Science 2026-05-12 Yu Wang , Sheng Shen , Rémi Munos , Hongyuan Zhan , Yuandong Tian

Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, this process often leads to catastrophic forgetting of the…

Machine Learning · Computer Science 2025-12-22 Joanna Sliwa , Frank Schneider , Philipp Hennig , Jose Miguel Hernandez-Lobato

Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer…

Machine Learning · Computer Science 2026-03-19 Yuxiang Ji , Ziyu Ma , Yong Wang , Guanhua Chen , Xiangxiang Chu , Liaoni Wu

Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and…

Artificial Intelligence · Computer Science 2018-09-21 Jakob N. Foerster , Richard Y. Chen , Maruan Al-Shedivat , Shimon Whiteson , Pieter Abbeel , Igor Mordatch

Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA training methods suffer from two critical limitations: poor…

Robotics · Computer Science 2026-05-25 Ruofan Jin , Zaixi Zhang

Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is computationally expensive and memory-intensive. Parameter-efficient fine-tuning (PEFT)…

Computation and Language · Computer Science 2026-05-12 Longteng Zhang , Lin Zhang , Shaohuai Shi , Xiaowen Chu , Bo Li

Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning. We propose \textbf{\textit{$\boldsymbol{\pi}$-StepNFT}}…

Robotics · Computer Science 2026-03-10 Siting Wang , Xiaofeng Wang , Zheng Zhu , Minnan Pei , Xinyu Cui , Cheng Deng , Jian Zhao , Guan Huang , Haifeng Zhang , Jun Wang

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some…

Artificial Intelligence · Computer Science 2026-03-05 Lu Yang , Zelai Xu , Minyang Xie , Jiaxuan Gao , Zhao Shok , Yu Wang , Yi Wu