Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
• 34
AI & ML interests
Scalable Artificial Intelligence
Recent Activity
View all activity
Papers
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
MInTRL: Off-policy Intervention can boost On-policy RL
Articles
amazon/ABO-Edit
Preview • Updated • 539
amazon/poiss
Updated • 21
amazon/Turnstile-Synthetic-Domains
Viewer • Updated • 100k • 221
amazon/ConfBench
Viewer • Updated • 1.35k • 1.53k • 1
amazon/kaputt
Updated • 1.56k • 4
amazon/music-off-policy-evaluation-benchmark
Viewer • Updated • 1.68M • 1.23k
amazon/AutoSUIT
Viewer • Updated • 951 • 1.35k
amazon/ShoppingReasoningBench
Viewer • Updated • 633 • 46 • 2
amazon/sop-bench
Viewer • Updated • 2.16k • 232 • 1
amazon/doc_split
Preview • Updated • 225 • 4
amazon/CodePrefBench
Preview • Updated • 71 • 2
amazon/AmazonQAC
Viewer • Updated • 396M • 522 • 18