Decoding the brain: From neural representations to mechanistic models

MW Mathis, AP Rotondo, EF Chang, AS Tolias… - Cell, 2024 - cell.com
A central principle in neuroscience is that neurons within the brain act in concert to produce
perception, cognition, and adaptive behavior. Neurons are organized into specialized brain …

Latent exploration for reinforcement learning

AS Chiappa, A Marin Vargas… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract In Reinforcement Learning, agents learn policies by exploring and interacting with
the environment. Due to the curse of dimensionality, learning policies that map high …

A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

P Liu, J Günster, N Funk, S Gröger… - Advances in …, 2025 - proceedings.neurips.cc
Abstract Machine learning methods have a groundbreaking impact in many application
domains, but their application on real robotic platforms is still limited. Despite the many …

Curriculum is more influential than haptic information during reinforcement learning of object manipulation against gravity

P Ojaghi, R Mir, A Marjaninejad, A Erwin… - arxiv preprint arxiv …, 2024 - arxiv.org
Learning to lift and rotate objects with the fingertips is necessary for autonomous in-hand
dexterous manipulation. In our study, we explore the impact of various factors on successful …

Contrastive abstraction for reinforcement learning

V Patil, M Hofmarcher, E Rumetshofer… - arxiv preprint arxiv …, 2024 - arxiv.org
Learning agents with reinforcement learning is difficult when dealing with long trajectories
that involve a large number of states. To address these learning problems effectively, the …

Curriculum Learning Influences the Emergence of Different Learning Trends

R Mir, P Ojaghi, A Erwin, A Marjaninejad… - 2024 IEEE-RAS 23rd …, 2024 - ieeexplore.ieee.org
Reinforcement learning (RL) algorithms are traditionally evaluated and compared by their
learning trends (ie, average performance) over trials and time. However, the presence of a …

Acquiring musculoskeletal skills with curriculum-based reinforcement learning

AS Chiappa, P Tano, N Patel, A Ingster, A Pouget… - bioRxiv, 2024 - biorxiv.org
Efficient, physiologically-detailed musculoskeletal simulators and powerful learning
algorithms provide new computational tools to tackle the grand challenge of understanding …

MyoChallenge 2024: Physiological Dexterity and Agility in Bionic Humans

V Caggiano, G Durandau, S Song, CK Tan… - … 2024 Competition Track - openreview.net
Limb loss represents a traumatic and destabilizing event in human life, significantly
impacting an individual's quality of life and independence. Advancements in bionic …