Reinforcement Learning with Quantitative Verification for Assured Multi-Agent Policies.
Joshua RileyRadu CalinescuColin PatersonDaniel KudenkoAlec BanksPublished in: ICAART (2) (2021)
Keyphrases
- reinforcement learning
- multi agent
- optimal policy
- reinforcement learning agents
- control policies
- cooperative multi agent systems
- policy search
- partially observable markov decision processes
- markov decision process
- multiagent reinforcement learning
- reward function
- state space
- markov decision problems
- function approximation
- multi agent systems
- reinforcement learning algorithms
- control policy
- hierarchical reinforcement learning
- model checking
- quantitative and qualitative
- markov decision processes
- multi agent reinforcement learning
- state abstraction
- multiple agents
- intelligent agents
- multi agent environments
- fitted q iteration
- function approximators
- multiagent systems
- decision problems
- learning agents
- learning algorithm
- infinite horizon
- transfer learning
- resolve conflicts
- qualitative and quantitative
- single agent
- model free
- dynamic programming
- temporal difference
- dynamic environments
- action selection
- formal verification
- learning process
- software agents
- machine learning
- agent oriented
- reinforcement learning methods
- verification method
- signature verification
- autonomous agents
- cooperative
- traffic signal control
- policy gradient methods