Generalized Neural Policies for Relational MDPs.
Sankalp GargAniket Bajpai MausamPublished in: CoRR (2020)
Keyphrases
- optimal policy
- markov decision processes
- markov decision process
- markov decision problems
- reinforcement learning
- policy search
- decision diagrams
- reward function
- fitted q iteration
- neural network
- state space
- relational data
- network architecture
- data model
- decision problems
- decision processes
- factored mdps
- relational databases
- neural model
- partially observable markov decision processes
- reinforcement learning algorithms
- finite horizon
- multi relational
- sufficient conditions
- linear programming
- dynamic programming
- average cost
- partially observable
- average reward
- statistical relational learning
- control policies
- finite state
- decision theoretic planning
- machine learning