Romane Cecchi
@romanececchi.bsky.social
Postdoc in the Human Reinforcement Learning team led by @stepalminteri.bsky.social at École Normale Supérieure (ENS) in Paris ✨
🧵 New preprint out!
📄 "Elucidating attentional mechanisms underlying value normalization in human reinforcement learning"
👁️ We show that visual attention during learning causally shapes how values are encoded
w/ @sgluth.bsky.social & @stepalminteri.bsky.social
🔗 doi.org/10.31234/osf...
📄 "Elucidating attentional mechanisms underlying value normalization in human reinforcement learning"
👁️ We show that visual attention during learning causally shapes how values are encoded
w/ @sgluth.bsky.social & @stepalminteri.bsky.social
🔗 doi.org/10.31234/osf...
OSF
doi.org
April 22, 2025 at 4:57 PM
🧵 New preprint out!
📄 "Elucidating attentional mechanisms underlying value normalization in human reinforcement learning"
👁️ We show that visual attention during learning causally shapes how values are encoded
w/ @sgluth.bsky.social & @stepalminteri.bsky.social
🔗 doi.org/10.31234/osf...
📄 "Elucidating attentional mechanisms underlying value normalization in human reinforcement learning"
👁️ We show that visual attention during learning causally shapes how values are encoded
w/ @sgluth.bsky.social & @stepalminteri.bsky.social
🔗 doi.org/10.31234/osf...
Reposted by Romane Cecchi
Epistemic biases in human reinforcement learning: behavioral evidence, computational characterization, normative status and possible applications.
A quite self-centered review, but with a broad introduction and conclusions and very cool figures.
Few main takes will follow
osf.io/preprints/ps...
A quite self-centered review, but with a broad introduction and conclusions and very cool figures.
Few main takes will follow
osf.io/preprints/ps...
January 23, 2025 at 3:47 PM
Epistemic biases in human reinforcement learning: behavioral evidence, computational characterization, normative status and possible applications.
A quite self-centered review, but with a broad introduction and conclusions and very cool figures.
Few main takes will follow
osf.io/preprints/ps...
A quite self-centered review, but with a broad introduction and conclusions and very cool figures.
Few main takes will follow
osf.io/preprints/ps...
Reposted by Romane Cecchi
New preprint! 🚨
Performance of standard reinforcement learning (RL) algorithms depends on the scale of the rewards they aim to maximize.
Inspired by human cognitive processes, we leverage a cognitive bias to develop scale-invariant RL algorithms: reward range normalization.
Curious? Have a read!👇
Performance of standard reinforcement learning (RL) algorithms depends on the scale of the rewards they aim to maximize.
Inspired by human cognitive processes, we leverage a cognitive bias to develop scale-invariant RL algorithms: reward range normalization.
Curious? Have a read!👇
December 10, 2024 at 6:02 PM
New preprint! 🚨
Performance of standard reinforcement learning (RL) algorithms depends on the scale of the rewards they aim to maximize.
Inspired by human cognitive processes, we leverage a cognitive bias to develop scale-invariant RL algorithms: reward range normalization.
Curious? Have a read!👇
Performance of standard reinforcement learning (RL) algorithms depends on the scale of the rewards they aim to maximize.
Inspired by human cognitive processes, we leverage a cognitive bias to develop scale-invariant RL algorithms: reward range normalization.
Curious? Have a read!👇
Reposted by Romane Cecchi
🚨New preprint alert!🚨
Achieving Scale-Invariant Reinforcement Learning Performance with Reward Range Normalization.
Where we show that things we discover in psychology can be useful for machine learning.
By the amazing
@maevalhotellier.bsky.social and Jeremy Perez.
doi.org/10.31234/osf...
Achieving Scale-Invariant Reinforcement Learning Performance with Reward Range Normalization.
Where we show that things we discover in psychology can be useful for machine learning.
By the amazing
@maevalhotellier.bsky.social and Jeremy Perez.
doi.org/10.31234/osf...
OSF
osf.io
December 5, 2024 at 3:22 PM
🚨New preprint alert!🚨
Achieving Scale-Invariant Reinforcement Learning Performance with Reward Range Normalization.
Where we show that things we discover in psychology can be useful for machine learning.
By the amazing
@maevalhotellier.bsky.social and Jeremy Perez.
doi.org/10.31234/osf...
Achieving Scale-Invariant Reinforcement Learning Performance with Reward Range Normalization.
Where we show that things we discover in psychology can be useful for machine learning.
By the amazing
@maevalhotellier.bsky.social and Jeremy Perez.
doi.org/10.31234/osf...