Related papers: EgoMap: Projective mapping and structured egocentr…
In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different…
Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, object-centric agents…
While Large Language Models (LLMs) possess significant capabilities in open-world agent tasks, they also face challenges in rapidly adapting to new, specialized tasks due to their reliance on static pre-trained knowledge. Traditional…
Our theoretical understanding of deep learning has not kept pace with its empirical success. While network architecture is known to be critical, we do not yet understand its effect on learned representations and network behavior, or how…
Understanding the behavior of deep reinforcement learning (DRL) agents -particularly as task and agent sophistication increase- requires more than simple comparison of reward curves, yet standard methods for behavioral analysis remain…
Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for effective long-term reasoning, traditional neuro-symbolic methods rely heavily on…
We propose a self-organizing memory architecture for perceptual experience, capable of supporting autonomous learning and goal-directed problem solving in the absence of any prior information about the agent's environment. The architecture…
Failure is inevitable for embodied navigation in complex environments. To enhance the resilience, replanning (RP) is a viable option, where the robot is allowed to fail, but is capable of adjusting plan until success. However, existing RP…
An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming…
Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…
Learning to perform activities through demonstration requires extracting meaningful information about the environment from observations. In this research, we investigate the challenge of planning high-level goal-oriented actions in a…
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently,…
This paper proposes an end-to-end deep reinforcement learning approach for mobile robot navigation with dynamic obstacles avoidance. Using experience collected in a simulation environment, a convolutional neural network (CNN) is trained to…
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the…
Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these…
In this work, we investigate how implicit neural feed back can accelerate reinforcement learning in complex robotic manipulation settings. While prior electroencephalogram (EEG) guided reinforcement learning studies have primarily focused…
Progress in Embodied AI has made it possible for end-to-end-trained agents to navigate in photo-realistic environments with high-level reasoning and zero-shot or language-conditioned behavior, but benchmarks are still dominated by…
The spiking activity of principal cells in mammalian hippocampus encodes an internalized neuronal representation of the ambient space---a cognitive map. Once learned, such a map enables the animal to navigate a given environment for a long…
Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired…
The ability to estimate temporal relationships is critical for both animals and artificial agents. Cognitive science and neuroscience provide remarkable insights into behavioral and neural aspects of temporal credit assignment. In…