Search papers, labs, and topics across Lattice.
3
0
2
SC3-Eval achieves a remarkable 0.929 Pearson correlation in evaluating robot policies, revealing critical insights into their real-world performance.
RQL achieves superior offline reinforcement learning performance by effectively utilizing prior data without the pitfalls of backpropagation through time.
Flow Reversal Steering transforms vague human commands into precise robotic actions, achieving up to 95% higher success rates in real-world tasks with minimal training.
