Reward Bound for Behavioral Guarantee of Model-based Planning Agents.
Zhiyu AnXianzhong DingWan DuPublished in: Tiny Papers @ ICLR (2024)
Keyphrases
- agent behavior
- reactive agents
- multi agent
- multi agent systems
- reinforcement learning
- multi agent planning
- decision theoretic
- multiagent systems
- multiple agents
- action selection
- autonomous agents
- single agent
- upper bound
- planning problems
- cooperative
- decentralized decision making
- learning agent
- agent architecture
- uncertain environments
- intelligent agents
- incomplete knowledge
- agent based simulation
- agent receives
- software agents
- lower bound
- resource allocation
- heuristic search
- artificial agents
- game theoretic
- decision making
- mobile agents
- agent systems
- information gathering
- complex domains
- complex environments
- domain independent
- partial observability
- agent model
- bandit problems
- planning process
- intelligent behavior
- real time strategy games
- reward function
- search algorithm
- planning domains