Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability.
Thomy PhanFabian RitzPhilipp AltmannMaximilian ZornJonas NüßleinMichael KölleThomas GaborClaudia Linnhoff-PopienPublished in: ICML (2023)
Keyphrases
- multi agent reinforcement learning
- partial observability
- learning agent
- reinforcement learning
- partially observable
- multi agent
- learning agents
- planning problems
- solving problems
- multi agent learning
- belief state
- markov decision process
- learning algorithm
- multi agent systems
- knowledge based systems
- state space
- single agent
- partially observable markov decision processes
- learning capabilities
- function approximation
- learning process