Concurrent reinforcement learning as a rehearsal for decentralized planning under uncertainty.
Landon KraemerBikramjit BanerjeePublished in: AAMAS (2013)
Keyphrases
- planning under uncertainty
- reinforcement learning
- multi agent
- markov decision processes
- partially observable markov decision processes
- dec pomdps
- decision theoretic
- robotic tasks
- optimal policy
- state space
- cooperative
- ai planning
- decision theoretic planning
- dynamical systems
- belief space
- finite state
- probabilistic planning
- partially observable
- multi agent systems
- machine learning
- infinite horizon
- continuous state
- markov decision process
- distributed systems
- multiple agents
- model free
- partially observable markov decision process
- decision making
- learning algorithm