Consistent epistemic planning for multiagent deep reinforcement learning.
Peiliang WuShicheng LuoLiqiang TianBingyi MaoWenbai ChenPublished in: Int. J. Mach. Learn. Cybern. (2024)
Keyphrases
- multi agent
- reinforcement learning
- single agent
- learning agents
- action selection
- multiagent systems
- planning problems
- cooperative
- state space
- multi agent systems
- decision support
- partially observable
- macro actions
- planning under uncertainty
- function approximation
- reinforcement learning problems
- belief change
- model free
- path finding
- intelligent agents
- multiagent learning
- mixed initiative
- ai planning
- heuristic search
- deterministic domains
- reward shaping
- stochastic domains
- robocup soccer
- reinforcement learning methods
- function approximators
- partially observable markov decision processes
- reinforcement learning algorithms
- markov decision processes