English
Related papers

Related papers: Generalizable Episodic Memory for Deep Reinforceme…

200 papers

Understanding the intricate operations of Recurrent Neural Networks (RNNs) mechanistically is pivotal for advancing their capabilities and applications. In this pursuit, we propose the Episodic Memory Theory (EMT), illustrating that RNNs…

Neural and Evolutionary Computing · Computer Science 2023-10-05 Arjun Karuvally , Peter Delmastro , Hava T. Siegelmann

We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate…

Machine Learning · Computer Science 2021-12-06 Hung Le , Majid Abdolshah , Thommen K. George , Kien Do , Dung Nguyen , Svetha Venkatesh

Offline reinforcement learning (RL) can fit strong value functions from fixed datasets, yet reliable deployment still hinges on the action selection interface used to query them. When the dataset induces a branched or multimodal action…

Machine Learning · Computer Science 2026-03-25 Haoyu Wang , Jingcheng Wang , Shunyu Wu , Xinwei Xiao

Memory is an important aspect of intelligence and plays a role in many deep reinforcement learning models. However, little progress has been made in understanding when specific memory systems help more than others and how well they…

Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully…

Machine Learning · Computer Science 2019-06-03 Yang Liu , Yunan Luo , Yuanyi Zhong , Xi Chen , Qiang Liu , Jian Peng

Reinforcement learning (RL) has driven breakthroughs in AI, from game-play to scientific discovery and AI alignment. However, its broader applicability remains limited by challenges such as low data efficiency and poor generalizability.…

Artificial Intelligence · Computer Science 2025-06-03 Xidong Yang , Wenhao Li , Junjie Sheng , Chuyun Shen , Yun Hua , Xiangfeng Wang

In this work, we consider one-shot imitation learning for object rearrangement tasks, where an AI agent needs to watch a single expert demonstration and learn to perform the same task in different environments. To achieve a strong…

Machine Learning · Computer Science 2022-11-29 Aviv Netanyahu , Tianmin Shu , Joshua Tenenbaum , Pulkit Agrawal

Machine learning, artificial intelligence and especially deep learning based approaches are often used to simplify or eliminate the burden of programming industrial robots. Using these approaches robots inherently learn a skill instead of…

Robotics · Computer Science 2021-04-22 Sanaz Behbahani , Siddharth Chhatpar , Said Zahrai , Vishakh Duggal , Mohak Sukhwani

Memory is critical for AI agents, yet the widely-adopted static memory, aiming to create readily available memory in advance, is inevitably subject to severe information loss. To address this limitation, we propose a novel framework called…

Computation and Language · Computer Science 2025-11-25 B. Y. Yan , Chaofan Li , Hongjin Qian , Shuqi Lu , Zheng Liu

Deep Reinforcement Learning agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training on new data. Replay Memories are a common solution to the problem, decorrelating…

Machine Learning · Computer Science 2023-08-29 Muhammad Burhan Hafez , Tilman Immisch , Tom Weber , Stefan Wermter

Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries,…

Robotics · Computer Science 2026-03-03 Ji Li , Bo Wang , Jing Xia , Mingyi Li , Shiyan Hu

In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based…

Machine Learning · Computer Science 2023-10-13 Zihao Xu , Xuan Tang , Yufei Shi , Jianfeng Zhang , Jian Yang , Mingsong Chen , Xian Wei

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, without updating model…

Artificial Intelligence · Computer Science 2026-01-30 Jun Wang

Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex…

Computation and Language · Computer Science 2026-02-11 Zhengxuan Lu , Dongfang Li , Yukun Shi , Beilun Wang , Longyue Wang , Baotian Hu

Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose…

Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary,…

Machine Learning · Computer Science 2024-10-17 Sihao Wu , Xingyu Zhao , Xiaowei Huang

Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model…

Machine Learning · Computer Science 2019-12-19 Tetiana Parshakova , Jean-Marc Andreoli , Marc Dymetman

Episodic control, inspired by the role of episodic memory in the human brain, has been shown to improve the sample inefficiency of model-free reinforcement learning by reusing high-return past experiences. However, the memory growth of…

Systems and Control · Electrical Eng. & Systems 2024-07-24 Mukul Chodhary , Kevin Octavian , SooJean Han

Episodic memory -- the ability to recall specific events grounded in time and space -- is a cornerstone of human cognition, enabling not only coherent storytelling, but also planning and decision-making. Despite their remarkable…

Computation and Language · Computer Science 2025-01-24 Alexis Huet , Zied Ben Houidi , Dario Rossi

State of the art deep reinforcement learning algorithms are sample inefficient due to the large number of episodes they require to achieve asymptotic performance. Episodic Reinforcement Learning (ERL) algorithms, inspired by the mammalian…

Machine Learning · Computer Science 2024-06-07 Ismael T. Freire , Adrián F. Amil , Paul F. M. J. Verschure