5 papers
TaskSense: Focusing on What Matters in World Models
SM Mazharul Islam, Manfred Huber
World models for visual control typically learn compact latent states by reconstructing observations, implicitly encouraging representations to preserve information across the enti…
Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control
SM Mazharul Islam, Manfred Huber
A policy in deep reinforcement learning (RL), either deterministic or stochastic, is commonly parameterized as a Gaussian distribution alone, limiting the learned behavior to be un…
Hippocampus-Inspired Cognitive Architecture (HICA) for Operant Conditioning
Deokgun Park, Md Ashaduzzaman Rubel Mondol, SM Mazharul Islam +1
The neural implementation of operant conditioning with few trials is unclear. We propose a Hippocampus-Inspired Cognitive Architecture (HICA) as a neural mechanism for operant cond…
SEDRo: A Simulated Environment for Developmental Robotics
Aishwarya Pothula, Md Ashaduzzaman Rubel Mondol, Sanath Narasimhan +2
Even with impressive advances in application-specific models, we still lack knowledge about how to build a model that can learn in a human-like way and do multiple tasks. To learn…
An Open-World Simulated Environment for Developmental Robotics
SM Mazharul Islam, Md Ashaduzzaman Rubel Mondol, Aishwarya Pothula +1
As the current trend of artificial intelligence is shifting towards self-supervised learning, conventional norms such as highly curated domain-specific data, application-specific l…