Reinforcement Learning

Feeds to Scour
SubscribedAll
Scoured 245 posts in 14.4 ms

SkyPilot Sandboxes: Run Agent Code on Your Own Kubernetes, at Scale

 🖥️Hypervisors  Content type: Blog
blog.skypilot.co··Hacker News

Political Division Is So Severe America Should Split in Two

 ⚙operating systems  Content type: Blog
3quarksdaily.com·

Robots are closing in on human-like judgments, addressing a key challenge in physical AI

 🤖Transformers
techxplore.com·

Semi-finalists confirmed in Secondary Schools Volleyball Competition

 🌍Distributed Systems
cbc.bb·

Central College News

 🔍Symbolic Execution  Content type: Academic
news.central.edu·

huggingface/OpenEnv: An interface library for RL post training with environments.

 🤖Transformers  Content type: Code
github.com··Cited by 1 article

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

 🔢vector embedding  Content type: Academic
arxiv.org·

Photos: Syracuse Views Through the Decades

 ⚡SIMD Optimization  Content type: Academic
news.syr.edu·

Failing to Ragebait the New Gemma

 🧮Memory Models
lesswrong.com·

Spotlight On: Dreamplug Technologies Private Limited (CRED), a New Principal Participating Organization

 🔐Cryptography  Content type: Blog
blog.pcisecuritystandards.org·

Social intelligence Arises Between Minds

 🤖Transformers
psychologytoday.com·

You're doing it wrong

 🔓binary exploitation  Content type: News
understandably.com·

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

 🔍Symbolic Execution  Content type: Academic
arxiv.org··Hacker News

Designing Incentives for Responsive Consensus Protocols

 🌍Distributed Systems
eprint.iacr.org·

AI Ready? Google Ads Maturity Model.

 🌍Distributed Systems
kaushik.net·

Why Robotics Is a Pre-Paradigm Field

 🤖Transformers  Content type: News
whattotelltherobot.com··Hacker News·Cited by 1 article

Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning

 🧮Memory Models  Content type: Academic
arxiv.org·

cakewalk wyrm

 🔍Symbolic Execution
thevalleybelow.id·

I got so mad at poke(rogue)like that I trained a RL agent to beat it for me

 🧮Memory Models
thiagolira.blot.im··Hacker News

Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information

 🔢vector embedding
venturebeat.com··Hacker News

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help