Jimmy Lee In the reinforcement learning arena I am working on, during the random generation we created an invincible Anthropic team #gamedev
Reinforcement Learning
by @jmac-ai.bsky.social
Feed for posts including "reinforcement learning" in them. Filtered to exclude replies, reposts. Sorted by Hacker News ranking.
Pull to refresh
Jimmy Lee 
koenfucius 1 / 2
Research by Frimer et al on 1.3 million tweets from US congress members 2009-19 finds incivility rose 23%, partly driven by reinforcement learning—uncivil tweets tended to get more engagement, which drove politicians to greater incivility: buff.ly/XUM0vK4 HT @jayvanbavel.bsky.social
Digital Brain This dog nags his owner until he plays piano, then sings along. Experts call it reinforcement learning, and smart breeds like labradors and border collies are especially good at it.
Colin A brain is not a database to be queried. It's a reinforcement learning agent to be trained.
AlternativeTo Mellum2.1 enhances coding-agent capabilities with a 12B model for codebases. It retains a 2.5B architecture, uses reinforcement learning, and speeds up requests by 1.6x. Available on Hugging Face. alternativeto.net/news/2026/1...
RLDM 📣 Save the date! RLDM 2027, the Multi-disciplinary Conference on Reinforcement Learning and Decision Making, is coming to Paris, July 6-9, 2027 🎉 Stay tuned for submission deadlines and more updates on our website rldm.org 👀
Open Encyclopedia of Cognitive Science bot Learning from trial and error involves a complex interplay of neural circuits and computational processes that extend far beyond simple reward… Reinforcement Learning by Anne GE Collins https://doi.org/10.21428/e2759450.36d1ca92 #CognitiveScience
Massimo (mirror) Training a bipedal robots to play soccer using deep reinforcement learning. Original post