Search Results for author:
Found 2 papers, 0 papers with code
Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm
Furthermore, with $\mathcal{O}(1/\varepsilon^{4})$ samples we prove that the optimal policy corresponding to the recovered reward is $\varepsilon$-close to the expert policy in total variation distance.
A safe exploration approach to constrained Markov decision processes
In particular, in contrast to existing CMDP approaches that ensure policy feasibility only upon convergence, our algorithm guarantees the feasibility of the policies during the learning process and converges to the $\varepsilon$-optimal policy with a sample complexity of $\tilde{\mathcal{O}}(\varepsilon^{-6})$.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
