Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer
Paper • 2610.41296 • Published • 7
Jaehyeon Son
Sondroid
AI & ML interests
None yet
Recent Activity
upvoted a paper about 16 hours ago
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer published a dataset 15 days ago
Sondroid/RoboCasa-DC updated a dataset 15 days ago
Sondroid/RoboCasa-DCOrganizations
None yet