Search papers, labs, and topics across Lattice.
2
0
4
34
Post-training techniques could be the key to overcoming the limitations of traditional imitation learning in autonomous driving, ensuring safer and more reliable vehicle behavior in complex environments.
By recasting the Hamilton-Jacobi-Bellman equation as a tractable Monte Carlo estimation, this work stabilizes physics-informed RL and unlocks its potential for high-dimensional control tasks.
