Learning Graphical State Transitions
نویسنده
چکیده
Graph-structured data is important in modeling relationships between multiple entities, and can be used to represent states of the world as well as many data structures. Li et al. (2016) describe a model known as a Gated Graph Sequence Neural Network (GGS-NN) that produces sequences from graph-structured input. In this work I introduce the Gated Graph Transformer Neural Network (GGTNN), an extension of GGS-NNs that uses graph-structured data as an intermediate representation. The model can learn to construct and modify graphs in sophisticated ways based on textual input, and also to use the graphs to produce a variety of outputs. For example, the model successfully learns to solve almost all of the bAbI tasks (Weston et al., 2016), and also discovers the rules governing graphical formulations of a simple cellular automaton and a family of Turing machines.
منابع مشابه
Inverse Reinforcement Learning with Locally Consistent Reward Functions
Existing inverse reinforcement learning (IRL) algorithms have assumed each expert’s demonstrated trajectory to be produced by only a single reward function. This paper presents a novel generalization of the IRL problem that allows each trajectory to be generated by multiple locally consistent reward functions, hence catering to more realistic and complex experts’ behaviors. Solving our generali...
متن کاملUsing Bayesian Networks for Discovering Temporal-State Transition Patterns in Hemodialysis
In this paper, we adopt Bayesian networks for discovering temporal-state transition patterns in the Hemodialysis process. Bayesian network is a graphical model that encodes probabilistic relationships among variables, and easily incorporatesnew instances to maintain rules up to date. We demonstrate the proposed method in representing the causal relationships between medical treatments and trans...
متن کاملLearning Stochastic Logical Automaton
This paper is concerned with algorithms for the logical generalisation of probabilistic temporal models from examples. The algorithms combine logic and probabilistic models through inductive generalisation. The inductive generalisation algorithms consist of three parts. The first part describes the graphical generalisation of state transition models. State transition models are generalised by a...
متن کاملBranching ratios of radiative transitions in O VI
We study the branching ratios of the allowed and forbidden radiative transitions among the rst few (9) ne structure levels of O VI using relativistic coupled cluster theory. We nd irregular patterns for a number of transitions with in n-complexes with n ≤ 4. We have used the exisiting values of the allowed electric dipole (E1) transition as a benchmark of our theory. Good agreement with the exi...
متن کاملPropagation Algorithms for Variational Bayesian Learning
Variational approximations are becoming a widespread tool for Bayesian learning of graphical models. We provide some theoretical results for the variational updates in a very general family of conjugate-exponential graphical models. We show how the belief propagation and the junction tree algorithms can be used in the inference step of variational Bayesian learning. Applying these results to th...
متن کاملImitation Learning Using Graphical Models
Imitation-based learning is a general mechanism for rapid acquisition of new behaviors in autonomous agents and robots. In this paper, we propose a new approach to learning by imitation based on parameter learning in probabilistic graphical models. Graphical models are used not only to model an agent’s own dynamics but also the dynamics of an observed teacher. Parameter tying between the agent-...
متن کامل