Search papers, labs, and topics across Lattice.
University of Edinburgh Politecnico di Milano
2
0
6
Optimal regret in adversarial MDPs with stochastic hard constraints is finally achieved, bridging the gap between existing upper and lower bounds by achieving $\widetilde{\mathcal{O}}(\sqrt{T}/\rho + 1/(d\rho))$ regret.
Forget hand-engineered reward shaping: PPO-LTL lets you specify complex safety requirements as LTL formulas and automatically penalizes violations during RL training.
