English
Related papers

Related papers: Solving Continuous Control with Episodic Memory

200 papers

Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to…

Machine Learning · Computer Science 2021-12-09 Andrew Kyle Lampinen , Stephanie C. Y. Chan , Andrea Banino , Felix Hill

In this paper we explore how actor-critic methods in deep reinforcement learning, in particular Asynchronous Advantage Actor-Critic (A3C), can be extended with agent modeling. Inspired by recent works on representation learning and…

Multiagent Systems · Computer Science 2019-07-24 Pablo Hernandez-Leal , Bilal Kartal , Matthew E. Taylor

Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance…

Artificial Intelligence · Computer Science 2017-04-18 Marochko Vladimir , Leonard Johard , Manuel Mazzara

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…

Computation and Language · Computer Science 2025-12-09 Alessandra Terranova , Björn Ross , Alexandra Birch

Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in…

Machine Learning · Statistics 2019-10-29 Kamil Ciosek , Quan Vuong , Robert Loftin , Katja Hofmann

We focus on a simulation-based optimization problem of choosing the best design from the feasible space. Although the simulation model can be queried with finite samples, its internal processing rule cannot be utilized in the optimization…

Machine Learning · Computer Science 2021-11-02 Kuo Li , Qing-Shan Jia , Jiaqi Yan

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Machine Learning · Computer Science 2019-03-21 Hung Le , Truyen Tran , Svetha Venkatesh

Event perception refers to people's ability to carve up continuous experience into meaningful discrete events. We speak of finishing our morning coffee, mowing the lawn, leaving work, etc. as singular occurrences that are localized in time…

Artificial Intelligence · Computer Science 2024-07-09 Will Hancock , Kenneth D. Forbus

In artificial intelligence, multi agent systems constitute an interesting typology of society modeling, and have in this regard vast fields of application, which extend to the human sciences. Logic is often used to model such kind of…

Artificial Intelligence · Computer Science 2019-09-23 Valentina Pitoni

Robotic manipulation often requires memory: occlusion and state changes can make decision-time observations perceptually aliased, making action selection non-Markovian at the observation level because the same observation may arise from…

Robotics · Computer Science 2026-03-26 Xinying Guo , Chenxi Jiang , Hyun Bin Kim , Ying Sun , Yang Xiao , Yuhang Han , Jianfei Yang

Complementary Learning Systems theory holds that intelligent agents need two learning systems. Semantic memory is encoded in the neocortex with dense, overlapping representations and acquires structured knowledge. Episodic memory is encoded…

Machine Learning · Computer Science 2025-09-03 Lucie Fontaine , Frédéric Alexandre

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

Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-training) on other related tasks. In this work, we propose a…

Machine Learning · Computer Science 2019-10-15 Jonathan Lebensold , William Hamilton , Borja Balle , Doina Precup

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon…

Artificial Intelligence · Computer Science 2026-01-12 Ruizhe Zhang , Xinke Jiang , Zhibang Yang , Zhixin Zhang , Jiaran Gao , Yuzhen Xiao , Hongbin Lai , Xu Chu , Junfeng Zhao , Yasha Wang

In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a…

Machine Learning · Computer Science 2020-01-16 Mario S. Holubar , Marco A. Wiering

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Machine Learning · Computer Science 2019-11-27 David Rolnick , Arun Ahuja , Jonathan Schwarz , Timothy P. Lillicrap , Greg Wayne

Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information. Existing memory systems typically follow a pipeline of…

Computation and Language · Computer Science 2026-01-30 Yimin Deng , Yuqing Fu , Derong Xu , Yejing Wang , Wei Ni , Jingtong Gao , Xiaopeng Li , Chengxu Liu , Xiao Han , Guoshuai Zhao , Xiangyu Zhao , Li Zhu , Xueming Qian

Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm,…

Multiagent Systems · Computer Science 2021-05-20 Filippos Christianos , Lukas Schäfer , Stefano V. Albrecht

When creating new reinforcement learning tasks, practitioners often accelerate the learning process by incorporating into the task several accessory components, such as breaking the environment interaction into independent episodes and…

Machine Learning · Computer Science 2025-12-09 Homayoon Farrahi , A. Rupam Mahmood

Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we…

Optimization and Control · Mathematics 2014-12-03 Steven Perkins , Panayotis Mertikopoulos , David S. Leslie
‹ Prev 1 3 4 5 6 7 10 Next ›