Publications

You can also find my articles on my Google Scholar profile.

Filter by tag: All computer vision, deep learning, graph neural networks, memory, multi-agent, navigation, partial observability, reinforcement learning, robotics

Papers

Investigating Memory in Model-Free RL with POPGym Arcade

Published in International Conference on Machine Learning (Spotlight, Top 2.2%), 2026

Tags: computer vision, deep learning, memory, partial observability, reinforcement learning

Investigating how and what deep policies learn under partial observability

Explore to Learn: Latent Exploration through Disentangled Synergy Patterns for Reinforcement Learning in Overactuated Control

Published in AAAI Conference on Artificial Intelligence (Oral, Top ~5%), 2026

Tags: deep learning, reinforcement learning, robotics

A two-stage framework that discovers muscle synergy patterns for efficient control in high-dimensional action spaces

Language-Conditioned Offline RL for Multi-Robot Navigation

Published in International Conference on Robotics and Automation, 2025

Tags: deep learning, multi-agent, navigation, reinforcement learning, robotics

Learning real-world multi-agent low-latency navigation policies in an LLM latent space

CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications

Published in Conference on Robot Learning, 2024

Tags: computer vision, deep learning, multi-agent, partial observability, robotics

A decentralized visual spatial foundation model for multi-robot pose estimation and bird’s-eye-view representation

Recurrent Reinforcement Learning with Memoroids

Published in Thirty-eighth Conference on Neural Information Processing Systems, 2024

Tags: memory, reinforcement learning

Revisiting how we model and train memory in RL

Reinforcement Learning with Fast and Forgetful Memory

Published in Thirty-seventh Conference on Neural Information Processing Systems, 2023

Tags: deep learning, memory, reinforcement learning

A new deep memory model based on human models of memory and designed specifically for RL

Generalised f-Mean Aggregation for Graph Neural Networks

Published in Thirty-seventh Conference on Neural Information Processing Systems, 2023

Tags: deep learning, graph neural networks, multi-agent

Learning an optimal aggregation function for GNNs

POPGym: Benchmarking Partially Observable Reinforcement Learning

Published in The Eleventh International Conference on Learning Representations, 2023

Tags: deep learning, memory, partial observability, reinforcement learning

A collection of partially observable environments and memory model baselines

Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning

Published in Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023

Tags: deep learning, graph neural networks, multi-agent

Encoding and decoding a variable number of inputs into a fixed-size latent representation

A framework for real-world multi-robot systems running decentralized GNN-based policies

Published in 2022 International Conference on Robotics and Automation (ICRA), 2022

Tags: graph neural networks, multi-agent, robotics

Running a distributed robot system using a GNN

Modeling Partially Observable Systems using Graph-Based Memory and Topological Priors

Published in The 4th Annual Learning for Dynamics and Control Conference, 2022

Tags: deep learning, graph neural networks, memory, reinforcement learning

Modeling memory as a graph using GNNs

Embodied Visual Navigation With Automatic Curriculum Learning in Real Environments

Published in IEEE Robotics and Automation Letters, 2022

Tags: computer vision, deep learning, navigation, reinforcement learning, robotics

Real-world visual navigation using curriculum learning and RL

Improving Visual Feature Extraction in Glacial Environments

Published in IEEE Robotics and Automation Letters, 2019

Tags: computer vision, robotics

Visual SLAM in snow and ice

A Spring Propelled Extreme Environment Robot for Off-world Cave Exploration

Published in IEEE Aerospace Conference, 2019

Tags: computer vision, robotics

Low-cost spring-launched microbots for exploring lunar and Martian pit skylights

Patents

Task Performing Agent Systems and Methods

Published in US Patent US12085947B2, UK Patent GB2598758B, Japan Patent JP7225292B2, 2024

Tags: reinforcement learning, robotics

Patent covering embodied visual navigation agents trained with reinforcement learning

Steven D. Morad

Publications

Papers

Patents