Informed POMDP: Leveraging Additional Information in Model-Based RL.
Gaspard LambrechtsAdrien BollandDamien ErnstPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- model free
- markov decision processes
- optimal policy
- state space
- continuous state
- markov decision process
- partially observable markov decision processes
- model free reinforcement learning
- policy evaluation
- multi agent
- function approximation
- finite state
- partially observable
- machine learning
- partially observable domains
- reinforcement learning methods
- belief state
- reinforcement learning algorithms
- dynamical systems
- planning problems
- control policies
- partial observability
- dynamic programming
- policy iteration
- planning under uncertainty
- transfer learning
- partially observable markov decision process
- search space
- knowledge base