5 papers
Investigating Memory in Model-Free RL with POPGym Arcade
Zekang Wang, Zhe He, Borong Zhang +2
How should we analyze memory in deep RL? We introduce tools for analyzing policies under partial observability and revealing how agents use memory to make decisions. To utilize the…
120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL
Xiaoming Liu, Borong Zhang, Qingbiao Li +1
The prevailing paradigm for image-goal visual navigation often assumes access to large-scale datasets, substantial pretraining, and significant computational resources. In this wor…
Learning Mixture Density via Natural Gradient Expectation Maximization
Yutao Chen, Jasmine Bayrooti, Steven Morad
Mixture density networks are neural networks that produce Gaussian mixtures to represent continuous multimodal conditional densities. Standard training procedures involve maximum l…
Recurrent Reinforcement Learning with Memoroids
Steven Morad, Chris Lu, Ryan Kortvelesy +3
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov sta…
CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications
Jan Blumenkamp, Steven Morad, Jennifer Gielis +1
Autonomous robot operation in unstructured environments is often underpinned by spatial understanding through vision. Systems composed of multiple concurrently operating robots add…