Related papers: Generalizable Episodic Memory for Deep Reinforceme…

Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…

Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future.…

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of…

Experience replay is an essential component in deep reinforcement learning (DRL), which stores the experiences and generates experiences for the agent to learn in real time. Recently, prioritized experience replay (PER) has been proven to…

Scalable multi-agent reinforcement learning (MARL) remains a central challenge for AI. Existing population-based methods, like Policy-Space Response Oracles, PSRO, require storing explicit policy populations and constructing full payoff…

The abilities to perceive, learn, and use generalities, similarities, classes, i.e., semantic memory (SM), is central to cognition. Machine learning (ML), neural network, and AI research has been primarily driven by tasks requiring such…

How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segmentation. In this work, a graph memory network is developed…

Verbalization of robot experience, i.e., summarization of and question answering about a robot's past, is a crucial ability for improving human-robot interaction. Previous works applied rule-based systems or fine-tuned deep models to…

Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement…

A widely held hypothesis for why generative recommendation (GR) models outperform conventional item ID-based models is that they generalize better. However, there is few systematic way to verify this hypothesis beyond a superficial…

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…

In this work, we present a memory-augmented approach for image-goal navigation. Earlier attempts, including RL-based and SLAM-based approaches have either shown poor generalization performance, or are heavily-reliant on pose/depth sensors.…

Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…

Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers require sampling a…

We investigate the properties of a recently proposed Gradient Echo Memory (GEM) scheme for information mapping between optical and atomic systems. We show that GEM can be described by the dynamic formation of polaritons in k-space. This…

Weak memory models are a consequence of the desire on part of architects to preserve all the uniprocessor optimizations while building a shared memory multiprocessor. The efforts to formalize weak memory models of ARM and POWER over the…

Realizing generalizable dynamic object manipulation on conveyor systems is important for enhancing manufacturing efficiency, as it eliminates specialized engineering for different scenarios. To this end, imitation learning emerges as a…

While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state…

The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns. Inspired by this, we explore a novel mechanism to improve model generalization via…

We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this setting is the so-called "catastrophic…