Related papers: Stable Hadamard Memory: Revitalizing Memory-Augmen…

Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer…

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We…

Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Transformers face a quadratic bottleneck in attention when scaling to long contexts. Recent approaches introduce recurrent memory to extend context beyond the current window, yet these often face a fundamental trade-off between theoretical…

Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory…

Recent advances in persona-centric memory have revealed the powerful capability of multi-agent systems in managing persona memory, especially in conversational scenarios. However, these complex frameworks often suffer from information loss…

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value…

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems from game playing and robotics have been solved with deep model-free methods. Unfortunately, the sample…

Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many current algorithms access a simulator to train with a large…

As multi-agent reinforcement learning (MARL) progresses towards solving larger and more complex problems, it becomes increasingly important that algorithms exhibit the key properties of (1) strong performance, (2) memory efficiency, and (3)…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Artificial autonomous agents and robots interacting in complex environments are required to continually acquire and fine-tune knowledge over sustained periods of time. The ability to learn from continuous streams of information is referred…

Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which…

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…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…

Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks and has become the state-of-the-art for visual object tracking. The model stores information from previous frames in a memory bank, enabling…

Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss…

LiDAR place recognition plays a crucial role in SLAM, robot navigation, and autonomous driving. However, existing LiDAR place recognition methods often struggle to adapt to new environments without forgetting previously learned knowledge, a…