English
Related papers

Related papers: Bootstrapped Q-learning with Context Relevant Obse…

200 papers

We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are…

Machine Learning · Computer Science 2022-11-11 John D. Co-Reyes , Yingjie Miao , Daiyi Peng , Esteban Real , Sergey Levine , Quoc V. Le , Honglak Lee , Aleksandra Faust

Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as…

Computation and Language · Computer Science 2020-04-08 Xusen Yin , Jonathan May

Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden "trap states" --…

Machine Learning · Computer Science 2025-05-23 Yuxuan Li , Yicheng Gao , Ning Yang , Stephen Xia

While deep reinforcement learning (RL) from pixels has achieved remarkable success, its sample inefficiency remains a critical limitation for real-world applications. Model-based RL (MBRL) addresses this by learning a world model to…

Machine Learning · Computer Science 2026-02-26 Weipu Zhang , Adam Jelley , Trevor McInroe , Amos Storkey , Gang Wang

Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the…

Computation and Language · Computer Science 2019-03-26 Prithviraj Ammanabrolu , Mark O. Riedl

Reinforcement learning (RL) is successful at learning to play games where the entire environment is visible. However, RL approaches are challenged in complex games like Starcraft II and in real-world environments where the entire…

Machine Learning · Computer Science 2021-08-13 Elizabeth Gilmour , Noah Plotkin , Leslie Smith

Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions,…

Machine Learning · Computer Science 2023-09-26 Nirbhay Modhe , Qiaozi Gao , Ashwin Kalyan , Dhruv Batra , Govind Thattai , Gaurav Sukhatme

In this work, we address the challenge of zero-shot generalization (ZSG) in Reinforcement Learning (RL), where agents must adapt to entirely novel environments without additional training. We argue that understanding and utilizing…

Machine Learning · Computer Science 2024-04-16 Tidiane Camaret Ndir , André Biedenkapp , Noor Awad

Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged…

Machine Learning · Computer Science 2020-11-05 Nino Vieillard , Olivier Pietquin , Matthieu Geist

We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors…

Machine Learning · Computer Science 2018-12-31 Chaochao Lu , Bernhard Schölkopf , José Miguel Hernández-Lobato

Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals.In TBG agent design and training process, balancing the efficiency and performance of the agent models…

Computation and Language · Computer Science 2022-09-13 Chen Chen , Yue Dai , Josiah Poon , Caren Han

Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled data in downstream tasks, particularly in data-to-text…

Computation and Language · Computer Science 2022-06-07 Pei Ke , Haozhe Ji , Zhenyu Yang , Yi Huang , Junlan Feng , Xiaoyan Zhu , Minlie Huang

Unsupervised object-centric representation (OCR) learning has recently drawn attention as a new paradigm of visual representation. This is because of its potential of being an effective pre-training technique for various downstream tasks in…

Machine Learning · Computer Science 2024-02-27 Jaesik Yoon , Yi-Fu Wu , Heechul Bae , Sungjin Ahn

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction…

Computation and Language · Computer Science 2018-05-30 Marco A. Valenzuela-Escárcega , Ajay Nagesh , Mihai Surdeanu

Meta-reinforcement learning (meta-RL) acquires meta-policies that show good performance for tasks in a wide task distribution. However, conventional meta-RL, which learns meta-policies by randomly sampling tasks, has been reported to show…

Machine Learning · Computer Science 2022-04-01 Morio Matsumoto , Hiroya Matsuba , Toshihiro Kujirai

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading…

Machine Learning · Computer Science 2019-09-05 Jacob Rafati , David C. Noelle

Despite its experimental success, Model-based Reinforcement Learning still lacks a complete theoretical understanding. To this end, we analyze the error in the cumulative reward using a contraction approach. We consider both stochastic and…

Machine Learning · Computer Science 2021-02-26 Ting-Han Fan , Peter J. Ramadge

Consider the scenario where a human cleans a table and a robot observing the scene is instructed with the task "Remove the cloth using which I wiped the table". Instruction following with temporal reasoning requires the robot to identify…

Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient…

Machine Learning · Computer Science 2021-01-06 Junhyuk Oh , Matteo Hessel , Wojciech M. Czarnecki , Zhongwen Xu , Hado van Hasselt , Satinder Singh , David Silver