Acquisition of Inducing Policy in Collaborative Robot Navigation Based on Multiagent Deep Reinforcement Learning.
Mitsuhiro KamezakiRyan OngShigeki SuganoPublished in: IEEE Access (2023)
Keyphrases
- robot navigation
- multi agent
- reinforcement learning
- continuous state
- policy search
- optimal policy
- autonomous mobile robot
- action selection
- markov decision process
- autonomous robots
- multiagent systems
- markov decision problems
- learning agents
- policy gradient
- single agent
- scene understanding
- markov decision processes
- control policy
- action space
- function approximation
- state space
- temporal difference
- reinforcement learning algorithms
- function approximators
- policy iteration
- reward function
- map building
- control policies
- multiagent learning
- landmark recognition
- partially observable
- partially observable markov decision processes
- multi agent systems
- dynamic programming
- state dependent
- state action
- model free
- topological map
- initially unknown
- learning algorithm
- high quality
- infinite horizon
- real time
- average reward
- decision problems
- partially observable markov decision process
- multiple agents
- machine learning