Dealing With Groups of Actions in Multiagent Markov Decision Processes.
Guillaume DebrasAbdel-Illah MouaddibLaurent JeanpierreSimon Le GloannecPublished in: IJCCI (ECTA) (2016)
Keyphrases
- markov decision processes
- planning under uncertainty
- decision theoretic planning
- partially observable
- multi agent
- action space
- state and action spaces
- decision processes
- action sets
- stochastic games
- reward function
- state space
- reinforcement learning
- finite state
- macro actions
- multiagent reinforcement learning
- optimal policy
- multiple agents
- infinite horizon
- dynamic programming
- transition matrices
- policy iteration
- finite horizon
- average cost
- reinforcement learning algorithms
- average reward
- decision theoretic
- dec pomdps
- multiagent systems
- semi markov decision processes
- reachability analysis
- cooperative
- partially observable markov decision process
- multi agent systems
- factored mdps
- machine learning
- model based reinforcement learning
- heuristic search
- sufficient conditions
- continuous state
- probabilistic planning
- markov decision problems
- situation calculus
- partially observable markov decision processes
- markov decision process