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 …

Pink noise is all you need: Colored noise exploration in deep reinforcement learning

O Eberhard, J Hollenstein, C Pinneri… - … Conference on Learning …, 2023‏ - openreview.net
In off-policy deep reinforcement learning with continuous action spaces, exploration is often
implemented by injecting action noise into the action selection process. Popular algorithms …

Latent exploration for reinforcement learning

AS Chiappa, A Marin Vargas… - Advances in Neural …, 2023‏ - 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 …

Sar: Generalization of physiological agility and dexterity via synergistic action representation

C Berg, V Caggiano, V Kumar - Autonomous Robots, 2024‏ - Springer
Learning effective continuous control policies in high-dimensional systems, including
musculoskeletal agents, remains a significant challenge. Over the course of biological …

[HTML][HTML] Acquiring musculoskeletal skills with curriculum-based reinforcement learning

AS Chiappa, P Tano, N Patel, A Ingster, A Pouget… - Neuron, 2024‏ - cell.com
Efficient musculoskeletal simulators and powerful learning algorithms provide computational
tools to tackle the grand challenge of understanding biological motor control. Our winning …

Musclevae: Model-based controllers of muscle-actuated characters

Y Feng, X Xu, L Liu - SIGGRAPH Asia 2023 Conference Papers, 2023‏ - dl.acm.org
In this paper, we present a simulation and control framework for generating biomechanically
plausible motion for muscle-actuated characters. We incorporate a fatigue dynamics model …

Myodex: a generalizable prior for dexterous manipulation

V Caggiano, S Dasari, V Kumar - … Conference on Machine …, 2023‏ - proceedings.mlr.press
Human dexterity is a hallmark of motor control behaviors. Our hands can rapidly synthesize
new behaviors despite the complexity (multi-articular and multi-joints, with 23 joints …

Natural and robust walking using reinforcement learning without demonstrations in high-dimensional musculoskeletal models

P Schumacher, T Geijtenbeek, V Caggiano… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Humans excel at robust bipedal walking in complex natural environments. In each step, they
adequately tune the interaction of biomechanical muscle dynamics and neuronal signals to …

Myochallenge 2022: Learning contact-rich manipulation using a musculoskeletal hand

V Caggiano, G Durandau, H Wang… - NeurIPS 2022 …, 2023‏ - proceedings.mlr.press
Manual dexterity has been considered one of the critical components for human evolution.
The ability to perform movements as simple as holding and rotating an object in the hand …

Open the black box: Step-based policy updates for temporally-correlated episodic reinforcement learning

G Li, H Zhou, D Roth, S Thilges, F Otto… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Current advancements in reinforcement learning (RL) have predominantly focused on
learning step-based policies that generate actions for each perceived state. While these …