Ching-An Cheng @ICML2025
@chinganc_rl
Followers
2K
Following
256
Media
20
Statuses
120
Senior Research Scientist at @Google Research, working on usable theory and algorithms for Reinforcement Learning, Generative Optimization, and Robotics
Redmond, WA
Joined March 2020
#Trace and #GenerativeOptimization enables training a new kind of agents and model architectures. Come to chat with us and learn how #Trace works behind the scene and its theory. We will present its poster at #NeurIPS2024 on Friday (4:30pm-7:30pm, E Exhibit Hall A-C #2709).
0
1
12
RT @BrandoHablando: 🔄 We were nominated for Oral+top 1 in the MATH-AI workshp at #ICML!. 🚨Why? ≈46 % of GitHub commits are AI-generated—bu….
0
15
0
We are organizing a workshop tomorrow at #icml25. Come join us and checkout the latest on programmatic representation and agent learning.
Our #ICML2025 Programmatic Representations for Agent Learning workshop will take place tomorrow, July 18th, at the West Meeting Room 301-305, exploring how programmatic representations can make agent learning more interpretable, generalizable, efficient, and safe! Come join us!
0
5
26
RT @shaohua0116: Our #ICML2025 Programmatic Representations for Agent Learning workshop will take place tomorrow, July 18th, at the West Me….
0
17
0
RT @allenainie: Provably Learning from Language Feedback. TLDR: RL theory can help us do better inference-time exploration with feedback.….
0
8
0
Super excited about this work done by our former intern @wanqiao_xu . We show Learning from Language Feedback (LLF) with LLM can be formally studied with provable no-regret learning algorithms. This result builds a foundation toward new theories for LLM learning and optimization.
Decision-making with LLM can be studied with RL! Can an agent solve a task with text feedback (OS terminal, compiler, a person) efficiently? How can we understand the difficulty? We propose a new notion of learning complexity to study learning with language feedback only. 🧵👇
1
1
18
RT @allenainie: Decision-making with LLM can be studied with RL! Can an agent solve a task with text feedback (OS terminal, compiler, a per….
0
24
0
Check out this new optimization framework ( by #DataRobot that can automatically search for "Pareto-optimal" solutions for agentic workflows. It's built on our LLM generative optimization framework #Trace. Excited to see more applications of #Trace! 😎.
github.com
syftr is an agent optimizer that helps you find the best agentic workflows for your budget. - datarobot/syftr
0
0
7
RT @shaohua0116: Our ICML & RLC workshops welcome contributions using programmatic representations as policies, reward functions, skill lib….
0
12
0
Organizers: Shao-Hua Sun @shaohua0116, Levi Lelis.@levilelis, Xinyun Chen @xinyun_chen_, Shreyas Kapur.@shreyaskapur, Jiayuan Mao @maojiayuan, Ching-An Cheng @chinganc_rl, Anqi Li @AnqiLi24, Kuang-Huei Lee @kuanghueilee, and Leslie Kaelbling.
0
0
1
Workshop on Programmatic Reinforcement Learning (RLC 2025).- Web page: - Submission Deadline: May 30, 2025, AoE.- Author Notification: June 15, 2025, AoE.- Workshop Date: August 5, 2025 @ Edmonton, Canada.
1
0
1
Programmatic Representations for Agent Learning (ICML 2025) .- Web page: - Submission Deadline: May 24, 2025, AoE .- Author Notification: June 7, 2025, AoE .- Workshop Date: July 18, 2025 @ Vancouver, Canada.
1
0
1
Started my new job at #Google Research recently. Super excited about what can be done here. 😎.
22
3
295
RT @RL_Conference: The RLC accepted workshops list is out (link in next tweet)!.Programmatic RL.Causal RL.RL and videogames.Inductive biase….
0
16
0
RT @MSFTResearch: Announcing AutoGen 0.4, fully reimagined library for building advanced agentic AI systems, developed to improve code qual….
0
176
0
MSR is hiring robotics researchers!! Good time to join! 😎.
I'm hiring researchers for my physically embodied AI & robotics team at MSR! 🤖👇. Physically embodied agents, both in the humanoid robot form and beyond, are the new computational platform of tomorrow. As with personal computers many decades ago, these.
0
4
32
RT @Andrey__Kolobov: I'm hiring researchers for my physically embodied AI & robotics team at MSR! 🤖👇. Physically….
0
12
0
Thanks for emailing. I've replied to some of you.
0
0
3
#NeurIPS2024 Super fun talking to tons of people yesterday. Like seeing people got genuinely surprised and laughed. Non stop 3 hrs talking. Finally the poster session is over and I can take a break :). Looking forward to seeing new research inspired by #Trace. Great job
1
1
24