繁體中文
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어

#reinforcementlearning 搜尋結果

ye_chenlu's profile picture. Ph.D. student at UIUC, interested in RL reasoning, agent
Chenlu Ye
 @ye_chenlu
年9月5日

PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 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

ye_chenlu's tweet image. PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 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
ye_chenlu's tweet image. PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 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
2
10
36
14
4千
Vehicles_MDPI's profile picture. Vehicles (ISSN 2624-8921) is #openaccess journal of #transportationscience and #engineering published online by @MDPIopenaccess. IF 2.2, CiteScore 5.3, EI.
Vehicles
 @Vehicles_MDPI
3 小時

🚗 Sim-to-Real Application of Reinforcement Learning Agents for Autonomous, Real Vehicle Drifting Read: mdpi.com/2624-8921/6/2/… #AutonomousDrifting #ReinforcementLearning

Vehicles_MDPI's tweet image. 🚗 Sim-to-Real Application of Reinforcement Learning Agents for Autonomous, Real Vehicle Drifting Read: mdpi.com/2624-8921/6/2/… #AutonomousDrifting #ReinforcementLearning
0
0
0
0
10
ceobillionaire's profile picture. Vincent Boucher, President of @Montreal_AI #MontrealAI | B. Sc. Physics, M. A. Govt. Policy Analysis and M. Sc. Aerospace Engineering | $AGI by AGI.Eth #AGI
AGI.Eth
@ceobillionaire
年9月28日

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning Qian et al.: arxiv.org/abs/2509.19736 #ArtificialIntelligence #DeepLearning #ReinforcementLearning

ceobillionaire's tweet image. UserRL: Training Interactive User-Centric Agent via Reinforcement Learning Qian et al.: arxiv.org/abs/2509.19736 #ArtificialIntelligence #DeepLearning #ReinforcementLearning
4
2
11
0
263
KirkDBorne's profile picture. Advisor to startups. Freelancer. Founder of @LeadershipData. Global Speaker. Top influencer #BigData #DataScience #AI #IoT #ML #B2B. PhD Astrophysics @Caltech
Kirk Borne
@KirkDBorne
年8月10日

Deep #ReinforcementLearning Hands-On — Practical easy-to-follow guide to RL from Q-learning and DQNs to PPO and RLHF: amzn.to/3MV9o60 [3rd Edition] v/ @PacktDataML —— #AI #MachineLearning #DeepLearning #DataScience #DataScientist —— 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼: 🟢Learn with…

KirkDBorne's tweet image. Deep #ReinforcementLearning Hands-On — Practical easy-to-follow guide to RL from Q-learning and DQNs to PPO and RLHF: amzn.to/3MV9o60 [3rd Edition] v/ @PacktDataML —— #AI #MachineLearning #DeepLearning #DataScience #DataScientist —— 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼: 🟢Learn with…
215
34
177
104
9千
SciRobotics's profile picture. Official Twitter account of the journal Science Robotics. Also find us on Facebook: https://t.co/EI6szHLWIb
Science Robotics
 @SciRobotics
年9月4日

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: scim.ag/3JIh7WF

2
54
285
92
16千
CarolineWang98's profile picture. PhD Student in MARL @UTCompSci | Student Researcher @GoogleDeepMind | ex @SonyAI_global @dukecompsci
Caroline Wang
 @CarolineWang98
年9月15日

[1/4] 🚀 We’re excited to announce the v1 release of JaxAHT – a new library for Ad Hoc Teamwork (AHT) research, built with JAX for speed & scalability! Check it out 👉 larg.github.io/jax-aht #AI #MARL #ReinforcementLearning #JAX #AdHocTeamwork

1
7
37
2
4千
_kedar_18's profile picture. BTech student | ML & Web Dev Enthusiast | Diplomacy Buff | DSA | https://t.co/cWsj6pVeLN | 🙇@imVkohli
kedar
@_kedar_18
年9月26日

Day 12 🦾 of becoming an ML Beast: Explored Reinforcement Learning – where an agent interacts with an environment, takes actions, and learns from rewards to improve decisions over time. #MachineLearning #ReinforcementLearning #AI #Learninginpublic #100daysofcoding

_kedar_18's tweet image. Day 12 🦾 of becoming an ML Beast: Explored Reinforcement Learning – where an agent interacts with an environment, takes actions, and learns from rewards to improve decisions over time. #MachineLearning #ReinforcementLearning #AI #Learninginpublic #100daysofcoding
_kedar_18's tweet image. Day 12 🦾 of becoming an ML Beast: Explored Reinforcement Learning – where an agent interacts with an environment, takes actions, and learns from rewards to improve decisions over time. #MachineLearning #ReinforcementLearning #AI #Learninginpublic #100daysofcoding
1
0
13
1
372
olivia_y_lee's profile picture. MS CS, BS SymSys @Stanford | Researcher @StanfordAILab @StanfordIPRL | Robotics & AI
Olivia Lee
 @olivia_y_lee
年7月29日

Enabling robots to improve autonomously via RL will be powerful, and dense shaping rewards can greatly facilitate RL. Our #IROS2025 paper presents a method leveraging VLMs to derive dense rewards for efficient autonomous RL. ⚡🦾 #Robotics #ReinforcementLearning 🧵1/5

4
12
119
78
9千
SciRobotics's profile picture. Official Twitter account of the journal Science Robotics. Also find us on Facebook: https://t.co/EI6szHLWIb
Science Robotics
 @SciRobotics
年8月20日

Scientists have developed a method based on #ReinforcementLearning that enables a robot to use its upper body to lift and flip a water jug. @ToyotaResearch Learn more in Science #Robotics: scim.ag/4oK6qmt

4
5
44
14
5千
amitrathore's profile picture. Entrepreneur, Investor, Awake. Building https://t.co/a4W5BXesWf 🧘🏽‍♂️ Protocols, Platforms, People. 🌎☀️ https://t.co/yWfYbSu0eK | Chat with AmitGPT at https://t.co/z9jXmSJxIb
Amit Rathore
 @amitrathore
年8月31日

In the Age of AI, start from First Principles. Unlock bottom-up design. Solve classes of problems, not isolated features. Think systems, not silos. Solve fundamentally. Scale exponentially. #AI #AIAgents #ReinforcementLearning #RAG #KnowledgeGraph #Orchestration

amitrathore's tweet image. In the Age of AI, start from First Principles. Unlock bottom-up design. Solve classes of problems, not isolated features. Think systems, not silos. Solve fundamentally. Scale exponentially. #AI #AIAgents #ReinforcementLearning #RAG #KnowledgeGraph #Orchestration
0
0
2
0
81
SatlokChannel's profile picture. SA News Channel Delivering fact-checked news & spiritual insights! Truth- That You Want To Know
SA News Channel
@SatlokChannel
年8月11日

7/10 Reinforcement Learning trains agents through trial and error to maximize rewards. It’s used in gaming, robotics, and real-time decision systems like traffic control. #ReinforcementLearning #AI #SmartSystems #DeepLearning #GameAI #AutonomousTech

SatlokChannel's tweet image. 7/10 Reinforcement Learning trains agents through trial and error to maximize rewards. It’s used in gaming, robotics, and real-time decision systems like traffic control. #ReinforcementLearning #AI #SmartSystems #DeepLearning #GameAI #AutonomousTech
2
85
103
0
555
ZappyZappy7's profile picture. Technology Evangelist. I spread the good news that innovative #technology has the potential to make the world a better place #innovation #robot #IoT #AI
T.Yamazaki
 @ZappyZappy7
年9月27日

ロボットアーム装着 四足歩行ロボットが 腕と脚を組み合わせて動かし、移動しながら物体を操作する rai-inst.com/resources/blog… #ReinforcementLearning #framework #WholeBody #flexible #LocoManipulation #ReLIC #RAIInstitute

1
7
35
7
2千
sp3akerstelios's profile picture. Xillions must vibe code
sp3aker2020
@sp3akerstelios
年8月10日

RL playgrounds 🚀🔨🔨 I am playing with the Unity ML agents (which isnt even very recent). The possibilities are insane. From simple tasks to complex challenges, AI agents are leveling up. #ReinforcementLearning #AI #Unity

sp3akerstelios's tweet image. RL playgrounds 🚀🔨🔨 I am playing with the Unity ML agents (which isnt even very recent). The possibilities are insane. From simple tasks to complex challenges, AI agents are leveling up. #ReinforcementLearning #AI #Unity
2
1
4
0
160
KirkDBorne's profile picture. Advisor to startups. Freelancer. Founder of @LeadershipData. Global Speaker. Top influencer #BigData #DataScience #AI #IoT #ML #B2B. PhD Astrophysics @Caltech
Kirk Borne
@KirkDBorne
年9月20日

Introduction to various #ReinforcementLearning #Algorithms: bit.ly/2UPHbSj ————— #DataScience #AI #MachineLearning #ML #DeepLearning #DataMining #Mathematics #Gamification ————— + See this foundational book (2nd edition): amzn.to/3UtbeAa

KirkDBorne's tweet image. Introduction to various #ReinforcementLearning #Algorithms: bit.ly/2UPHbSj ————— #DataScience #AI #MachineLearning #ML #DeepLearning #DataMining #Mathematics #Gamification ————— + See this foundational book (2nd edition): amzn.to/3UtbeAa
8
20
86
48
4千
andrewroche99's profile picture. Digital Marketer & Problem Solver | #marketing | #SEO | #leadership | #AI | #GoBlue | All views are mine.
Andrew Roche
@andrewroche99
8 小時

Inverse reinforcement learning infers reward functions from observing expert behavior. Instead of programming rewards, AI learns what experts value by watching them. Learning goals from demonstrations. #ReinforcementLearning #InverseRL #LearningObjectives andrewroche.ai/ai-reinforceme…

andrewroche99's tweet card. Learn about the basics of AI reinforcement learning, how it works & practical applications—a perfect guide for entry-level students starting their AI journey.
AI Reinforcement Learning: A Beginner’s How-To Guide
來源: andrewroche.ai
0
0
0
0
7
ZappyZappy7's profile picture. Technology Evangelist. I spread the good news that innovative #technology has the potential to make the world a better place #innovation #robot #IoT #AI
T.Yamazaki
 @ZappyZappy7
年9月3日

アスリートのように考え、計画し、動くロボット自転車 rai-inst.com/resources/blog… 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
81
210
42
13千
Vehicles_MDPI's profile picture. Vehicles (ISSN 2624-8921) is #openaccess journal of #transportationscience and #engineering published online by @MDPIopenaccess. IF 2.2, CiteScore 5.3, EI.
Vehicles
 @Vehicles_MDPI
3 小時

🚗 Sim-to-Real Application of Reinforcement Learning Agents for Autonomous, Real Vehicle Drifting Read: mdpi.com/2624-8921/6/2/… #AutonomousDrifting #ReinforcementLearning

Vehicles_MDPI's tweet image. 🚗 Sim-to-Real Application of Reinforcement Learning Agents for Autonomous, Real Vehicle Drifting Read: mdpi.com/2624-8921/6/2/… #AutonomousDrifting #ReinforcementLearning
0
0
0
0
10
andrewroche99's profile picture. Digital Marketer & Problem Solver | #marketing | #SEO | #leadership | #AI | #GoBlue | All views are mine.
Andrew Roche
@andrewroche99
8 小時

Inverse reinforcement learning infers reward functions from observing expert behavior. Instead of programming rewards, AI learns what experts value by watching them. Learning goals from demonstrations. #ReinforcementLearning #InverseRL #LearningObjectives andrewroche.ai/ai-reinforceme…

andrewroche99's tweet card. Learn about the basics of AI reinforcement learning, how it works & practical applications—a perfect guide for entry-level students starting their AI journey.
AI Reinforcement Learning: A Beginner’s How-To Guide
來源: andrewroche.ai
0
0
0
0
7
andresvilarino's profile picture. Do something today that your future self will thank you for. #MIBer de @ISDI_edu Instagram: @andresvilarino https://t.co/fnQVD12DzP
Andres Vilariño 🇪🇦
 @andresvilarino
15 小時

#RA3: Mid-Training with Temporal Action Abstractions for Faster #ReinforcementLearning (RL) Post-Training in Code #LLMs buff.ly/LXLMNyi

andresvilarino's tweet image. #RA3: Mid-Training with Temporal Action Abstractions for Faster #ReinforcementLearning (RL) Post-Training in Code #LLMs buff.ly/LXLMNyi
0
0
0
0
7
huan__wang's profile picture. Director @ Salesforce Research. Research Interest: Large Language Model, Action Agent, Reinforcement Learning, Time Series Analytics, Learning Theory.
Huan Wang
 @huan__wang
年10月12日

Congrats to the team for building Webscale-RL, an automated data pipeline that turns pretraining corpora into verifiable RL data at trillion-token scale. Excited to see this bridge the gap between pretraining and RL! @SFResearch #AI #LLMs #ReinforcementLearning #MachineLearning

SFResearch's profile picture. We advance state-of-the-art #AI techniques paving the path for innovative products at @Salesforce. Focus areas: #AIAgents, #EnterpriseAI, #EGI, and #TrustedAI.
Salesforce AI Research
@SFResearch
年10月10日

📣 Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels 📣 RL for LLMs faces a critical data bottleneck: existing RL datasets are <10B tokens while pretraining uses >1T tokens. Our Webscale-RL pipeline solves this by automatically converting pretraining…

SFResearch's tweet image. 📣 Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels 📣 RL for LLMs faces a critical data bottleneck: existing RL datasets are &amp;lt;10B tokens while pretraining uses &amp;gt;1T tokens. Our Webscale-RL pipeline solves this by automatically converting pretraining…
1
6
28
18
15千
0
0
3
1
466
YouAccel's profile picture. Empowering learners worldwide with cutting-edge skills in AI, tech, business & digital innovation. Learn. Grow. Succeed with YouAccel! 🚀📚 #YouAccel
YouAccel
 @YouAccel
年10月11日

Reinforcement learning is a transformative AI approach where machines learn through trial and error, akin to human learning. Unlike traditional programming, it allows AI systems to... #ReinforcementLearning #ArtificialIntelligence #MachineLearning youaccel.com/blog/reinforce…

YouAccel's tweet card. Artificial intelligence (AI) often seems like a distant, almost mystical frontier, yet it’s one that’s already reshaping our lives in profound ways. At the hear...
Reinforcement Learning: Empowering Artificial Intelligence Through the Magic of Rewards
來源: youaccel.com
0
0
0
0
18
JamesBurre50244's profile picture. Econ + CS @ USFCA. Passionate about ML, NLP, and HAI. Focused on research and building impactful projects.
James Burrell
 @JamesBurre50244
年10月11日

Finished chapters 1–8 of Sutton & Barto’s Reinforcement Learning. Reading alongside Stanford’s CS234 lectures, great combo so far. Any recs for what to read next once I finish? #reinforcementlearning

0
0
0
0
16
ecomputerbooks's profile picture. Free Computer, Programming, Mathematics, Technical Books, Lecture Notes and Tutorials
Free Computer Books
 @ecomputerbooks
年10月11日

(Open Access) Distributional Reinforcement Learning: freecomputerbooks.com/Distributional… Look for "Read and Download Links" section to download. Follow me if you like this post. #ReinforcementLearning #MachineLearning #DeepLearning #LLMs #GenAI #GenerativeAI #NeuralNetworks

ecomputerbooks's tweet image. (Open Access) Distributional Reinforcement Learning: freecomputerbooks.com/Distributional… Look for &quot;Read and Download Links&quot; section to download. Follow me if you like this post. #ReinforcementLearning #MachineLearning #DeepLearning #LLMs #GenAI #GenerativeAI #NeuralNetworks
0
0
0
1
20
researchhires's profile picture. Empowering Minds, Connecting Futures in Academia
Researchhires
 @researchhires
年10月10日

Postdoctoral Researcher in Reinforcement Learning 📍ETH Zurich, Institute of Machine Learning, Switzerland Online, Multi-Agent & Human Feedback RL. Apply now: researchhires.com/position/ea709… #Postdoc #ReinforcementLearning #AIResearch #MachineLearning #AcademicJobs #ResearchHires

researchhires's tweet card. ResearchHires is the leading platform for professors to easily post and manage PhD, doctorate, master's, and intern research positions across Canadian universities. Students can search and apply for...
ResearchHires | Find and Post Research Positions ( PhD, Postdoc and Masters)
來源: researchhires.com
0
0
0
0
65
ecomputerbooks's profile picture. Free Computer, Programming, Mathematics, Technical Books, Lecture Notes and Tutorials
Free Computer Books
 @ecomputerbooks
年10月10日

(Open Access) Reinforcement Learning: An Introduction - freecomputerbooks.com/Reinforcement-… Look for "Read and Download Links" section to download. Follow me if you like this post. #ReinforcementLearning #MachineLearning #DeepLearning #LLMs #GenAI #GenerativeAI #NeuralNetworks

ecomputerbooks's tweet image. (Open Access) Reinforcement Learning: An Introduction - freecomputerbooks.com/Reinforcement-… Look for &quot;Read and Download Links&quot; section to download. Follow me if you like this post. #ReinforcementLearning #MachineLearning #DeepLearning #LLMs #GenAI #GenerativeAI #NeuralNetworks
0
0
0
0
22
scampbell1380's profile picture.
S C Campbell-Green
 @scampbell1380
年10月10日

📉 Errors aren’t failures; they’re learning vectors. Talus Labs trains agents to evolve through error feedback. @Talus_Labs #ReinforcementLearning #AI

0
0
0
0
7
neptune_ai's profile picture. Experiment tracker purpose-built for foundation model training. We tweet about #LLM best practices & other cool stuff. Read our blog at https://t.co/4eACuib1QI
neptune.ai
@neptune_ai
年10月10日

“Usually, the first idea doesn't check out. That's just the nature of #AIresearch.” For Derek Li, Senior Researcher at Noah's Ark Lab, that first idea was training all multitask #reinforcementlearning objectives together. What went wrong: Runs underperformed baselines, with…

0
0
0
0
88
Deluthium's profile picture. Democratize Liquidity. AI-powered efficiency. the 1st insti-grade onchain liquidity infra, backed by @ambergroup_io @flock_io
Deluthium
@Deluthium
年10月9日

Every swap, limit order, cross-chain action, it’s input to the #ReinforcementLearning engine. In #Deluthium, your request becomes part of the learning feedback loop. No black boxes. Full transparency. Brought to you by the Onchain Flash Boys. Powered by RL.

Deluthium's tweet image. Every swap, limit order, cross-chain action, it’s input to the #ReinforcementLearning engine. In #Deluthium, your request becomes part of the learning feedback loop. No black boxes. Full transparency. Brought to you by the Onchain Flash Boys. Powered by RL.
3
33
44
2
17千
reyemtech's profile picture.
Reyem Tech
 @reyemtech
年10月9日

Reinforcement learning AI skills are advancing quickly, creating a split in tech capabilities. Leaders ignoring this risk falling behind. Prioritize where AI momentum builds. reyemte.ch/jrh #AI #ReinforcementLearning

reyemtech's tweet card. AI tasks that work well with reinforcement learning are getting better fast — and threatening to leave the rest of the industry behind.
The reinforcement gap — or why some AI skills improve faster than others   | TechCrunch
來源: techcrunch.com
0
0
1
0
4
jushuT's profile picture. 四柱推命学・姓名判断学・易学・手相・人相・墓相・印相・風水家相学・気学・五行易等鑑定師範保持。 ◎週刊女性（通巻２３１３号）に{徹底調査「当たる！」と評判の占い師５０人}に取り上げられる （３ヶ月先まで対面鑑定の予約が入る人気占い師。正確無比な診断が世代を選ばず支持されている。）
臼井允絃
 @jushuT
年10月9日

📉 Errors aren’t failures; they’re learning vectors. Talus Labs trains agents to evolve through error feedback. @Talus_Labs #ReinforcementLearning #AI

0
0
0
0
1
nikoz9997's profile picture.
Nikoz9997
 @nikoz9997
年10月9日

⚙️ A model becomes intelligent when it changes itself. Talus Labs programs that reflexivity into machine agents. @Talus_Labs #ReinforcementLearning #AI

0
0
0
0
4
jewelleryxy's profile picture.
Alexander Santini
 @jewelleryxy
年10月9日

💫 Intelligence scales when feedback deepens. Talus Labs builds recursive systems that learn through their own outputs. @Talus_Labs #ReinforcementLearning #AI

0
0
1
0
9
AstroLabAI's profile picture. Astro Lab is an experimental AI platform that brings together industry and startups to accelerate AI growth.
Astro-Lab.AI
 @AstroLabAI
年10月9日

Meet PASTA: An RL agent that refines text-to-image results collaboratively, reducing trial-and-error. 🤖🎨 #PASTA #ReinforcementLearning

1
0
0
0
3
ye_chenlu's profile picture. Ph.D. student at UIUC, interested in RL reasoning, agent
Chenlu Ye
 @ye_chenlu
年9月5日

PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 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

ye_chenlu's tweet image. PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 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 &amp;amp; ORM. #LLM #ReinforcementLearning
ye_chenlu's tweet image. PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 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 &amp;amp; ORM. #LLM #ReinforcementLearning
2
10
36
14
4千
SatlokChannel's profile picture. SA News Channel Delivering fact-checked news & spiritual insights! Truth- That You Want To Know
SA News Channel
@SatlokChannel
年8月11日

7/10 Reinforcement Learning trains agents through trial and error to maximize rewards. It’s used in gaming, robotics, and real-time decision systems like traffic control. #ReinforcementLearning #AI #SmartSystems #DeepLearning #GameAI #AutonomousTech

SatlokChannel's tweet image. 7/10 Reinforcement Learning trains agents through trial and error to maximize rewards. It’s used in gaming, robotics, and real-time decision systems like traffic control. #ReinforcementLearning #AI #SmartSystems #DeepLearning #GameAI #AutonomousTech
2
85
103
0
555
ceobillionaire's profile picture. Vincent Boucher, President of @Montreal_AI #MontrealAI | B. Sc. Physics, M. A. Govt. Policy Analysis and M. Sc. Aerospace Engineering | $AGI by AGI.Eth #AGI
AGI.Eth
@ceobillionaire
年9月28日

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning Qian et al.: arxiv.org/abs/2509.19736 #ArtificialIntelligence #DeepLearning #ReinforcementLearning

ceobillionaire's tweet image. UserRL: Training Interactive User-Centric Agent via Reinforcement Learning Qian et al.: arxiv.org/abs/2509.19736 #ArtificialIntelligence #DeepLearning #ReinforcementLearning
4
2
11
0
263
_kedar_18's profile picture. BTech student | ML & Web Dev Enthusiast | Diplomacy Buff | DSA | https://t.co/cWsj6pVeLN | 🙇@imVkohli
kedar
@_kedar_18
年9月26日

Day 12 🦾 of becoming an ML Beast: Explored Reinforcement Learning – where an agent interacts with an environment, takes actions, and learns from rewards to improve decisions over time. #MachineLearning #ReinforcementLearning #AI #Learninginpublic #100daysofcoding

_kedar_18's tweet image. Day 12 🦾 of becoming an ML Beast: Explored Reinforcement Learning – where an agent interacts with an environment, takes actions, and learns from rewards to improve decisions over time. #MachineLearning #ReinforcementLearning #AI #Learninginpublic #100daysofcoding
_kedar_18's tweet image. Day 12 🦾 of becoming an ML Beast: Explored Reinforcement Learning – where an agent interacts with an environment, takes actions, and learns from rewards to improve decisions over time. #MachineLearning #ReinforcementLearning #AI #Learninginpublic #100daysofcoding
1
0
12
1
372
GoogleResearch's profile picture. Impossible? Let’s see. From algorithms to neuroscience to AI, Google Research strives to progress science, advance society & improve billions of people’s lives.
Google Research
@GoogleResearch
年6月4日

Today on the blog we propose Action-Based Contrastive Self-Training, a data-efficient #ReinforcementLearning tuning approach for improving multi-turn conversation modeling in mixed-initiative LLM interaction. Read all about it →goo.gle/3Sxas2T

GoogleResearch's tweet image. Today on the blog we propose Action-Based Contrastive Self-Training, a data-efficient #ReinforcementLearning tuning approach for improving multi-turn conversation modeling in mixed-initiative LLM interaction. Read all about it →goo.gle/3Sxas2T
0
8
88
24
5千
sp3akerstelios's profile picture. Xillions must vibe code
sp3aker2020
@sp3akerstelios
年8月10日

RL playgrounds 🚀🔨🔨 I am playing with the Unity ML agents (which isnt even very recent). The possibilities are insane. From simple tasks to complex challenges, AI agents are leveling up. #ReinforcementLearning #AI #Unity

sp3akerstelios's tweet image. RL playgrounds 🚀🔨🔨 I am playing with the Unity ML agents (which isnt even very recent). The possibilities are insane. From simple tasks to complex challenges, AI agents are leveling up. #ReinforcementLearning #AI #Unity
2
1
4
0
160
KirkDBorne's profile picture. Advisor to startups. Freelancer. Founder of @LeadershipData. Global Speaker. Top influencer #BigData #DataScience #AI #IoT #ML #B2B. PhD Astrophysics @Caltech
Kirk Borne
@KirkDBorne
年9月20日

Introduction to various #ReinforcementLearning #Algorithms: bit.ly/2UPHbSj ————— #DataScience #AI #MachineLearning #ML #DeepLearning #DataMining #Mathematics #Gamification ————— + See this foundational book (2nd edition): amzn.to/3UtbeAa

KirkDBorne's tweet image. Introduction to various #ReinforcementLearning #Algorithms: bit.ly/2UPHbSj ————— #DataScience #AI #MachineLearning #ML #DeepLearning #DataMining #Mathematics #Gamification ————— + See this foundational book (2nd edition): amzn.to/3UtbeAa
8
20
86
48
4千
my_cat_can_code's profile picture. CS PhD @UCSB 🎓 | All in ASI 📖 | Stealth Mode 😈 | Prev. DAOlivia co-founder 🤍 | Building for this universe 🌌 | @stanford @google
Zichen Chen (🐱,💖)
@my_cat_can_code
2024年9月26日

🚀 Exciting News! Our paper has been accepted at @NeurIPSConf! 🎉 We introduce State Chrono Representation (SCR) -- a novel approach in #ReinforcementLearning. SCR integrates long-term temporal dynamics and cumulative rewards into state representations, addressing key challenges…

my_cat_can_code's tweet image. 🚀 Exciting News! Our paper has been accepted at @NeurIPSConf! 🎉 We introduce State Chrono Representation (SCR) -- a novel approach in #ReinforcementLearning. SCR integrates long-term temporal dynamics and cumulative rewards into state representations, addressing key challenges…
0
7
104
36
14千
ceobillionaire's profile picture. Vincent Boucher, President of @Montreal_AI #MontrealAI | B. Sc. Physics, M. A. Govt. Policy Analysis and M. Sc. Aerospace Engineering | $AGI by AGI.Eth #AGI
AGI.Eth
@ceobillionaire
年5月4日

Automated Design of Agentic Systems Shengran Hu, Cong Lu, Jeff Clune: arxiv.org/abs/2408.08435 #ArtificialIntelligence #DeepLearning #ReinforcementLearning

ceobillionaire's tweet image. Automated Design of Agentic Systems Shengran Hu, Cong Lu, Jeff Clune: arxiv.org/abs/2408.08435 #ArtificialIntelligence #DeepLearning #ReinforcementLearning
1
1
3
1
232
ceobillionaire's profile picture. Vincent Boucher, President of @Montreal_AI #MontrealAI | B. Sc. Physics, M. A. Govt. Policy Analysis and M. Sc. Aerospace Engineering | $AGI by AGI.Eth #AGI
AGI.Eth
@ceobillionaire
年7月13日

The Bitter Lesson "Search and learning are general purpose methods that continue to scale with increased computation, even as the available computation becomes very great." — Richard Sutton Rich Sutton: incompleteideas.net/IncIdeas/Bitte… #ReinforcementLearning

ceobillionaire's tweet image. The Bitter Lesson &quot;Search and learning are general purpose methods that continue to scale with increased computation, even as the available computation becomes very great.&quot; — Richard Sutton Rich Sutton: incompleteideas.net/IncIdeas/Bitte… #ReinforcementLearning
3
4
8
1
438
Mkm_world's profile picture. Data science | Robotics | AI/ML. AI Champion. 2x Hackathon Winner. 2x AI Research Awardee. Mr. Algorithm 2024. Believer ✝️
Kayode Makinde
 @Mkm_world
2024年7月28日

Had an incredible time yesterday at #TECHMEET Abeokuta 3.0! 🎉 Spoke about the future of AI and why #ReinforcementLearning deserves more attention. Great discussions on how can AI can be leveraged and the positive impact on future careers! 🚀 #AI #TechEvent #Abeokuta

Mkm_world's tweet image. Had an incredible time yesterday at #TECHMEET Abeokuta 3.0! 🎉 Spoke about the future of AI and why #ReinforcementLearning deserves more attention. Great discussions on how can AI can be leveraged and the positive impact on future careers! 🚀 #AI #TechEvent #Abeokuta
Mkm_world's tweet image. Had an incredible time yesterday at #TECHMEET Abeokuta 3.0! 🎉 Spoke about the future of AI and why #ReinforcementLearning deserves more attention. Great discussions on how can AI can be leveraged and the positive impact on future careers! 🚀 #AI #TechEvent #Abeokuta
Mkm_world's tweet image. Had an incredible time yesterday at #TECHMEET Abeokuta 3.0! 🎉 Spoke about the future of AI and why #ReinforcementLearning deserves more attention. Great discussions on how can AI can be leveraged and the positive impact on future careers! 🚀 #AI #TechEvent #Abeokuta
Mkm_world's tweet image. Had an incredible time yesterday at #TECHMEET Abeokuta 3.0! 🎉 Spoke about the future of AI and why #ReinforcementLearning deserves more attention. Great discussions on how can AI can be leveraged and the positive impact on future careers! 🚀 #AI #TechEvent #Abeokuta
3
9
46
0
1千
weijiawu7's profile picture. https://t.co/VKqU85kIhb
weijia wu
 @weijiawu7
年8月12日

🚀 New Survey: Reinforcement Learning in Vision We review 200+ works spanning MLLMs, visual generation, unified models & VLA — from RLHF to GRPO & RLVR. 🔗 Paper: arxiv.org/abs/2508.08189 🔗 Resources: github.com/weijiawu/Aweso… #AI #ReinforcementLearning #ComputerVision #Survey

weijiawu7's tweet image. 🚀 New Survey: Reinforcement Learning in Vision We review 200+ works spanning MLLMs, visual generation, unified models &amp;amp; VLA — from RLHF to GRPO &amp;amp; RLVR. 🔗 Paper: arxiv.org/abs/2508.08189 🔗 Resources: github.com/weijiawu/Aweso… #AI #ReinforcementLearning #ComputerVision #Survey
1
6
22
8
2千

Something went wrong.


Something went wrong.


United States Trends