Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Imitation Learning in Relational Domains: A Functional-Gradient Boosting Approach

Citations in the corpus

• Fitted Q-Learning for Relational Domains (2020, methodology): “an be used to model probabilistic action choices. While it is conceivable to learn policies directly as performed by policy gradient approach of Kersting and Driessens (2008) or imitation learning by Natarajan et al. (2011), our methods approximate the Qvalues or the Bellman error using gradient boo”
• Human-Guided Learning for Probabilistic Logic Models (2018, methodology): “This method has been extended to various relational models for learning the structure (Kersting and Driessens, 2008; Karwath et al., 2008; Natarajan et al., 2011; Natarajan et al., 2012).”
• Structure learning for relational logistic regression: an ensemble approach (2018, methodology): “Inspired by the recent successes of non-parametric learning methods for SRL models [8, 16, 33, 31, 32], we develop a non-parametric learning method for full model learning (structure and parameters) of RLR models.”
• Policies for Active Learning from Demonstration (2017, background): “…Reinforcement Learning (Abbeel and Ng 2004; Tastan and Sukthankar 2011), Dynamic Bayesian Networks (such as HMMs) (Dereszyn-ski et al. 2011; Onta˜n´on, Monta˜na, and Gonzalez 2014), and supervised learning techniques (Sammut et al. 1992) (including relational approaches (Natarajan et al. 2011)).”