We propose a Represent And Mimic (RAMi) framework for training 1) an identifiable latent representation to capture the independent factors of variation for the objects and 2) a mimic tree that extracts the causal impact of the latent features on DRL action values.
As with propositional (non-relational) graphical models, the major scalability bottleneck for model discovery is computing instantiation counts: the number of times a relational pattern is instantiated in a database.
Distributional Reinforcement Learning (RL) differs from traditional RL by estimating the distribution over returns to capture the intrinsic uncertainty of MDPs.
We propose a score-based DAG structure learning method for time-series data that captures linear, nonlinear, lagged and instantaneous relations among variables while ensuring acyclicity throughout the entire graph.
Our experiments demonstrate a significant improvement in the realism of the generated graph structures, typically by 1-2 orders of magnitude of graph structure metrics, compared to leading graph VAEand GAN models.
This paper develops a new approach for agent representations, based on a Markov game model, that is tailored towards applications in professional ice hockey.
As a by-product we also obtain a characterization for when a given distribution over size-$k$ structures is the statistical frequency distribution of size-$k$ sub-structures in much larger size-$n$ structures.
An LMUT is learned using a novel on-line algorithm that is well-suited for an active play setting, where the mimic learner observes an ongoing interaction between the neural net and the environment.
A subtle difference between propositional and relational data is that in many relational models, marginal probabilities depend on the population or domain size.
The metric is based on the likelihood ratio of two parameter vectors: One that represents the population associations, and another that represents the individual associations.
To assess a player's overall performance, we introduce a novel Game Impact Metric (GIM) that aggregates the values of the player's actions.
Successful previous approaches have built a predictive model based on player features, or derived performance predictions from the observed performance of comparable players in a cohort.
A searchable meta-database provides metadata (e. g., the number of tables in the database, the number of rows and columns in the tables, the number of foreign key constraints between tables).
A multi-relational statistical model provides an integrated analysis of the heterogeneous and interdependent data resources in the database.
To support our position, we have developed the FACTORBASE system, which uses SQL as a high-level scripting language for statistical-relational learning of a graphical model structure.
We describe an approach for learning both the RDN's structure and its parameters, given an input relational database: First learn a Bayesian network (BN), then transform the Bayesian network to an RDN.
With a naive enumeration approach, computing sufficient statistics for negative relationships is feasible only for small databases.