On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract).
Vincent François-LavetGuillaume RabusseauJoelle PineauDamien ErnstRaphael FonteneauPublished in: IJCAI (2020)
Keyphrases
- extended abstract
- partial observability
- reinforcement learning
- partially observable
- symbolic model checking
- markov decision process
- planning problems
- state space
- learning agent
- function approximation
- belief space
- fully observable
- partially observable markov decision processes
- belief state
- planning under partial observability
- markov decision processes
- markov decision problems
- partial information
- reinforcement learning algorithms
- decision problems
- optimal policy
- learning capabilities
- multi agent