Explore tweets tagged as #Reinforcementlearning
@SciRobotics
Science Robotics
8 days
Scientists have designed a #ReinforcementLearning-based framework that enables multiple robot arms to perform up to 40 tasks simultaneously without colliding in a crowded workspace. @GoogleDeepMind Learn more in Science #Robotics: https://t.co/B7HDD3lsIL
2
54
279
@ye_chenlu
Chenlu Ye
7 days
PROF🌀Right answer, flawed reason?🤔🌀 📄 https://t.co/8kFrxKQbVW Excited to share our work: PROF-PRocess cOnsistency Filter! 🚀 Challenge: ORM is blind to flawed logic, and PRM suffers from reward hacking. Our method harmonizes strengths of PRM & ORM. #LLM #ReinforcementLearning
Tweet media one
Tweet media two
2
9
32
@ZappyZappy7
T.Yamazaki
9 days
アスリートのように考え、計画し、動くロボット自転車 https://t.co/DanO8MLvrI パルクールの機動性と、どんなに複雑な地形も知覚して計画し、ナビゲートする知性を兼ね備える #ReinforcementLearning #UltraMobileVehicle #UMV #JumpingBicycle #RAI_Institute
1
82
208
@GThoppe
Gugan Thoppe
12 hours
Excited to deliver a four-lecture #ReinforcementLearning tutorial at IIIT Hyderabad @iiithyd for the @IndiaACM Winter School 2025 (AI & Finance) scheduled from December 8 to 13. More details soon. Link: https://t.co/nGybCQL5Iy #RL
0
0
3
@ZappyZappy7
T.Yamazaki
6 days
4
27
105
@arianazmoudeh
Arian Azmoudeh
8 days
Agentic AI is moving from sci-fi to enterprise reality. 🤖 Systems that learn, adapt, and act, powered by reinforcement learning and multimodal input are reshaping how work gets done. 🔄⚠️ Buckle up 🚀 #AgenticAI #AIagents #ReinforcementLearning #Multimodal #FutureTech
Tweet media one
1
0
2
@LabsRainier
Rainier Labs
2 days
Training new RL policies on Terrier 002 using our trusty training gantry 🦿 Step by step, we’re building smarter, more adaptive legged robots — and sharing the journey as we go. #buildinpublic #Robotics #ReinforcementLearning #AI #TerrierRobot
Tweet media one
Tweet media two
Tweet media three
0
0
2
@oluwadoyin41112
LammieCodes😎
6 days
Day 19 of 40🚀. Built my first Reinforcement learning architecture using pytorch. #40daysofcode #reinforcementlearning #Artificialintelligence
Tweet media one
Tweet media two
0
0
6
@oluwadoyin41112
LammieCodes😎
7 days
Day 18 of 40🚀. - I learnt about action selection policies(softmax, E-greedy(1-E)). - Started a new project. #40daysofcode #reinforcementlearning
Tweet media one
1
0
3
@talkingrobotics
Talking Robotics
10 days
🚀We are back for another season 🤖Join us for #86 with Nicolas Perrin-Gilbert from ISIR. 🔗Details: https://t.co/stmwxztbR4 📅Date: September 03, 2025 (Wed) at 18:00 CEST | 12:00 EDT | 09:00 PDT 🖊️Zoom Registration: https://t.co/6L3wV3PV5K #robotics #Reinforcementlearning
Tweet media one
0
1
5
@philfung
pfung
5 days
This rant is so on point. Really wish Nvidia would get its act together. https://t.co/87QCZ7xWSP
Tweet media one
0
0
2
@griffintaur
Griffintaur
4 days
🚀 Interestingresearch: Symbolic Graphics Programming with Large Language Models Read more: https://t.co/ITcaw2UAi6 #LLM #ReinforcementLearning #MLResearch
0
0
2
@oluwadoyin41112
LammieCodes😎
10 days
Day 15 of 40🚀. Started a Course on re-inforcement Learning. I Learnt how it works. I learnt on bellman's equation. #40daysofcode #reinforcementlearning #ml
0
0
2
@shubhtrips
Shubhankar Tripathy
3 days
CoRL unites generation and understanding in one RL framework for multimodal LLMs—boosting text→image outputs by 7% and understanding benchmarks by 23%. A leap in unified multimodal learning! https://t.co/T9dqj9kdh6 #MultimodalAI #ReinforcementLearning #AI #MachineLearning
0
0
2
@oluwadoyin41112
LammieCodes😎
8 days
Day 17 of 40 🚀. I continued on my reinforcement learning course. Learnt about: - Temporal difference - deep Q learning intuition learning and action - experience replay. #40daysofcode #ReinforcementLearning #artifici
0
0
2