XLVIN: eXecuted Latent Value Iteration Nets.
Andreea DeacPetar VelickovicOgnjen MilinkovicPierre-Luc BaconJian TangMladen NikolicPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- state space
- heuristic search
- latent variables
- markov decision chains
- partially observable markov
- information retrieval
- policy iteration
- dynamic programming
- co occurrence
- category labels
- markov decision process
- optimal policy
- database
- least squares
- high dimensional
- multiscale
- website
- neural network
- data sets