On the Expressivity of Markov Reward (Extended Abstract).
David AbelWill DabneyAnna HarutyunyanMark K. HoMichael L. LittmanDoina PrecupSatinder SinghPublished in: IJCAI (2022)
Keyphrases
- extended abstract
- reinforcement learning
- markov model
- markov chain
- semi markov
- long run
- conditional independence
- computational properties
- markov process
- multi agent
- real time
- reward function
- markov processes
- data mining
- inverse reinforcement learning
- partially observable environments
- dynamic programming
- relational databases
- objective function
- image processing
- metadata
- knowledge base
- artificial intelligence
- real world
- data sets