Fri, Jul 10, 2026 8:00 AM–5:00 PM KST @ Grand Ballroom 101-102

Posters: Hall A 912–917, 1000–1015, 1100–1115, 1200–1201

This workshop explores a shift beyond human preference signals by treating world feedback 🌍 —measurable signals from real-world interactions such as efficiency, safety, health, performance, and economic outcomes—as a first-class training signal for reinforcement learning systems. The goal of this workshop is to move beyond human feedback to train reinforcement learning systems using world-grounded learning signals (e.g., efficiency, safety, and economic outcomes) that better reflect the true consequences of agent behavior. Bringing together researchers across reinforcement learning, foundation models, robotics, systems, and AI alignment, it focuses on how to model and integrate heterogeneous, noisy, and delayed feedback into modern learning pipelines. Through invited talks, contributed papers, and interactive panels, the workshop aims to clarify core challenges, develop shared frameworks, and advance scalable, robust, and deployable learning paradigms grounded in real-world consequences.

Speakers

Panelists

Schedule

• 8:00–8:10 Opening remarks

• 8:10–8:40  Invited talk 1 - Benjamin Eysenbach & Catherine (Cathy) Ji: The Geometry of Empowerment (remote)

• 8:40–9:10  Invited talk 2 - Jerry Tworek: Fifty shades of self-improvement (remote)

• 9:10–10:00 Oral presentations

• 10:00–10:30 Coffee break

• 10:30–11:00 Invited talk 3 - Brian Zhan: The RL Environment Land Grab: What's Worth Backing and What Won't Work

• 11:00–12:00 Poster session 1 (Hall A 912–917, 1000–1015, 1100–1115, 1200–1201)

• 12:00–13:00 Lunch

• 13:00–13:30 Invited talk 4 - Jesse Zhang: Beyond Human Feedback: Synthetic Preferences for Scalable Robot Reinforcement Learning

• 13:30–14:00 Invited talk 5 - Chelsea Finn: Beyond the Scalar Reward Bottleneck

• 14:00–15:00 Poster session 2 (Hall A 912–917, 1000–1015, 1100–1115, 1200–1201)

• 15:00–15:30 Coffee break

• 15:30–16:00 Invited talk 6 - Roberta Raileanu: Superhuman Scientific Discovery

• 16:00–17:00 Panel discussion (Brian Zhan, Jesse Zhang, Roberta Raileanu, Yilun Du, and Yiding Jiang)

Poster Instruction

• Location: Hall A, poster boards 912–917, 1000–1015, 1100–1115, and 1200–1201.

• Capacity: Each poster board accommodates two posters.

• Board assignment: There are no pre-assigned boards. You may display your poster on any available board within the ranges listed above on a first-come, first-served basis.

Organizers

Contact

rlxf2026@gmail.com

Sponsors

• NTU AI-CoRE (Artificial Intelligence Center of Research Excellence)