Abstract: This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes ...
One might intall only a subset of the dependencies: @article{RoyGBNXT_2023_pos2LTL, doi = {10.1609/aaai.v37i5.25800}, url = {https://doi.org/10.1609%2Faaai.v37i5 ...