arxiv:2310.15145
Max Sobol Mark
maxsobolmark
ยท
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
authored
a paper
12 months ago
Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for
Autonomous Real-World Reinforcement Learning
Organizations
Papers
1
models
None public yet
datasets
None public yet