Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring.
Merlijn KraleThiago D. SimãoNils JansenPublished in: ICAPS (2023)
Keyphrases
- partially observable environments
- reinforcement learning
- reinforcement learning algorithms
- partially observable
- inverse reinforcement learning
- state space
- markov decision processes
- function approximation
- cooperative games
- multi agent
- dynamic programming
- temporal difference
- partially observable markov decision processes