Multi-Agent Exploration for Faster and Reliable Deep Q-Learning Convergence in Reinforcement Learning.
Abhijit MajumdarPatrick BenavidezMo M. JamshidiPublished in: WAC (2018)
Keyphrases
- reinforcement learning
- multi agent
- exploration strategy
- action selection
- stochastic approximation
- function approximation
- reinforcement learning algorithms
- multi agent reinforcement learning
- single agent
- state space
- model free
- faster convergence
- learning algorithm
- temporal difference learning
- temporal difference
- exploration exploitation tradeoff
- optimal control
- markov decision processes
- optimal policy
- cooperative
- convergence rate
- machine learning
- continuous state and action spaces
- partially observable
- control problems
- learning agents
- convergence speed
- model based reinforcement learning
- actor critic
- multi agent systems
- multiagent learning
- autonomous learning
- continuous state
- learning problems
- policy evaluation
- learning process
- reinforcement learning methods
- active exploration
- traffic signal control
- transfer learning
- learning capabilities