Follow
Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs. (arXiv:2210.15755v1 [cs.LG]) http://arxiv.org/abs/2210.15755
Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs. (arXiv:2210.15755v1 [cs.LG]) http://arxiv.org/abs/2210.15755