Pink noise is all you need: Colored noise exploration in deep reinforcement learning
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 …
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 …, 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 …
the environment. Due to the curse of dimensionality, learning policies that map high …
Myodex: a generalizable prior for dexterous manipulation
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 …
new behaviors despite the complexity (multi-articular and multi-joints, with 23 joints …
Sar: Generalization of physiological agility and dexterity via synergistic action representation
C Berg, V Caggiano, V Kumar - arXiv preprint arXiv:2307.03716, 2023 - arxiv.org
Learning effective continuous control policies in high-dimensional systems, including
musculoskeletal agents, remains a significant challenge. Over the course of biological …
musculoskeletal agents, remains a significant challenge. Over the course of biological …
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 …
The ability to perform movements as simple as holding and rotating an object in the hand …
Natural and robust walking using reinforcement learning without demonstrations in high-dimensional musculoskeletal models
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 …
adequately tune the interaction of biomechanical muscle dynamics and neuronal signals to …
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Current advancements in reinforcement learning (RL) have predominantly focused on
learning step-based policies that generate actions for each perceived state. While these …
learning step-based policies that generate actions for each perceived state. While these …
MuscleVAE: Model-Based Controllers of Muscle-Actuated Characters
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 …
plausible motion for muscle-actuated characters. We incorporate a fatigue dynamics model …
Replication of Impedance Identification Experiments on a Reinforcement-Learning-Controlled Digital Twin of Human Elbows
This study presents a pioneering effort to replicate human neuromechanical experiments
within a virtual environment utilising a digital human model. By employing MyoSuite, a state …
within a virtual environment utilising a digital human model. By employing MyoSuite, a state …
Self Model for Embodied Intelligence: Modeling Full-Body Human Musculoskeletal System and Locomotion Control with Hierarchical Low-Dimensional …
Modeling and control of the human musculoskeletal system is important for understanding
human motion, developing embodied intelligence, and optimizing human-robot interaction …
human motion, developing embodied intelligence, and optimizing human-robot interaction …