English
Related papers

Related papers: Self-Guided Plan Extraction for Instruction-Follow…

200 papers

To successfully tackle challenging manipulation tasks, autonomous agents must learn a diverse set of skills and how to combine them. Recently, self-supervised agents that set their own abstract goals by exploiting the discovered structure…

Machine Learning · Computer Science 2022-02-01 Andrii Zadaianchuk , Georg Martius , Fanny Yang

Various techniques have been proposed to improve large language models (LLMs) adherence to formatting and instruction constraints. One of the most effective approaches involves utilizing high-quality data generated by powerful models.…

Computation and Language · Computer Science 2025-07-09 Sihyun Park

Although substantial efforts have been made to mitigate catastrophic forgetting in continual learning, the intrinsic mechanisms are not well understood. In this work, we demonstrate the existence of "pseudo forgetting": the performance…

Machine Learning · Computer Science 2025-06-10 Huashan Sun , Yizhe Yang , Yinghao Li , Jiawei Li , Yang Gao

Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world. However, the grounding problem still hinders the applications of LLMs in the real-world…

Computation and Language · Computer Science 2023-09-06 Shaohui Peng , Xing Hu , Qi Yi , Rui Zhang , Jiaming Guo , Di Huang , Zikang Tian , Ruizhi Chen , Zidong Du , Qi Guo , Yunji Chen , Ling Li

Language agents powered by large language models (LLMs) are increasingly valuable as decision-making tools in domains such as gaming and programming. However, these agents often face challenges in achieving high-level goals without detailed…

Computation and Language · Computer Science 2024-06-10 Ruihan Yang , Jiangjie Chen , Yikai Zhang , Siyu Yuan , Aili Chen , Kyle Richardson , Yanghua Xiao , Deqing Yang

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches…

Artificial Intelligence · Computer Science 2025-04-18 Zheng Wang , Shu Xian Teo , Jun Jie Chew , Wei Shi

Reinforcement learning agents usually learn from scratch, which requires a large number of interactions with the environment. This is quite different from the learning process of human. When faced with a new task, human naturally have the…

Artificial Intelligence · Computer Science 2020-05-22 Peng Zhang , Jianye Hao , Weixun Wang , Hongyao Tang , Yi Ma , Yihai Duan , Yan Zheng

Reinforcement learning (RL) is an effective method of finding reasoning pathways in incomplete knowledge graphs (KGs). To overcome the challenges of a large action space, a self-supervised pre-training method is proposed to warm up the…

Computation and Language · Computer Science 2025-04-17 Ying Ma , Owen Burns , Mingqiu Wang , Gang Li , Nan Du , Laurent El Shafey , Liqiang Wang , Izhak Shafran , Hagen Soltau

One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs…

Computation and Language · Computer Science 2024-07-19 Guanting Dong , Keming Lu , Chengpeng Li , Tingyu Xia , Bowen Yu , Chang Zhou , Jingren Zhou

Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can…

Human-Computer Interaction · Computer Science 2018-06-25 Xinlei Pan , Eshed Ohn-Bar , Nicholas Rhinehart , Yan Xu , Yilin Shen , Kris M. Kitani

Reinforcement Learning (RL) agents have great successes in solving tasks with large observation and action spaces from limited feedback. Still, training the agents is data-intensive and there are no guarantees that the learned behavior is…

Artificial Intelligence · Computer Science 2021-10-20 Helge Spieker

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which…

Machine Learning · Computer Science 2026-03-25 Pengsen Liu , Maosen Zeng , Nan Tang , Kaiyuan Li , Jing-Cheng Pang , Yunan Liu , Yang Yu

Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imitation learning often provides a more convenient and…

Artificial Intelligence · Computer Science 2024-03-20 Jianlan Luo , Perry Dong , Yuexiang Zhai , Yi Ma , Sergey Levine

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Computation and Language · Computer Science 2020-05-20 Felix Hill , Sona Mokra , Nathaniel Wong , Tim Harley

Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via…

Machine Learning · Computer Science 2019-11-19 Sujoy Paul , Jeroen van Baar , Amit K. Roy-Chowdhury

Deep Reinforcement Learning (RL) techniques can benefit greatly from leveraging prior experience, which can be either self-generated or acquired from other entities. Action advising is a framework that provides a flexible way to transfer…

Machine Learning · Computer Science 2021-07-01 Ercument Ilhan , Jeremy Gow , Diego Perez-Liebana

Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training may be insufficient or outdated. Conditioning generation on…

Computation and Language · Computer Science 2025-03-04 Matthew Finlayson , Ilia Kulikov , Daniel M. Bikel , Barlas Oguz , Xilun Chen , Aasish Pappu

Training intelligent agents to navigate highly interactive environments presents significant challenges. While guided meta reinforcement learning (RL) approach that first trains a guiding policy to train the ego agent has proven effective…

Robotics · Computer Science 2024-10-29 Mansur Arief , Mike Timmerman , Jiachen Li , David Isele , Mykel J Kochenderfer

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Artificial Intelligence · Computer Science 2026-03-31 Xiaoying Zhang , Zichen Liu , Yipeng Zhang , Xia Hu , Wenqi Shao

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Machine Learning · Computer Science 2020-05-28 Yiming Ding , Carlos Florensa , Mariano Phielipp , Pieter Abbeel