Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
Paper • 2605.12380 • Published • 2
Rasool Fakoor
rasoolfa
AI & ML interests
Building embodied agents.
Recent Activity
upvoted a paper 20 days ago
Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training updated a model 8 months ago
FundamentalResearchLabs/oct20-qw4-midtraining-lr5e7-oci-4k-2984891-c1b734ab-s312 updated a model 8 months ago
FundamentalResearchLabs/oct20-qw4-midtraining-lr5e7-oci-4k-2984891-c1b734ab-s624Organizations
None yet
upvoted a paper 20 days ago
upvoted an article about 1 year ago
Article
Efficient LLM Pretraining: Packed Sequences and Masked Attention
sirluk
• • 71