On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies.
Blai BonetDominik DrexlerHector GeffnerPublished in: CoRR (2024)
Keyphrases
- optimal policy
- management policies
- control policies
- highly expressive
- markov decision problems
- markov decision process
- decision processes
- transport systems
- allocation policies
- allocation policy
- language learning
- policy search
- policy gradient methods
- revenue management
- state dependent
- access control policies
- dynamic programming
- special case
- natural language
- partially observable markov decision processes
- asymptotically optimal
- infinite horizon
- markov decision processes
- expected reward
- programming language
- optimal pricing
- state space