Function approximation based multi-agent reinforcement learning

2006 ◽

Vol 06 (03) ◽

pp. 413-428 ◽

Cited By ~ 1

Author(s):

DEAN C. WARDELL ◽

GILBERT L. PETERSON

Keyword(s):

Reinforcement Learning ◽

Function Approximation ◽

Hill Climbing ◽

Individual Agent ◽

Q Learning ◽

Stochastic Environments ◽

State Aggregation ◽

Multi Agent ◽

Fuzzy State ◽

Better Than

Reinforcement learning is one of the more attractive machine learning technologies, due to its unsupervised learning structure and ability to continually learn even as the operating environment changes. Additionally, by applying reinforcement learning to multiple cooperative software agents (a multi-agent system) not only allows each individual agent to learn from its own experience, but also opens up the opportunity for the individual agents to learn from the other agents in the system, thus accelerating the rate of learning. This research presents the novel use of fuzzy state aggregation, as the means of function approximation, combined with the fastest policy hill climbing methods of Win or Lose Fast (WoLF) and policy-dynamics based WoLF (PD-WoLF). The combination of fast policy hill climbing and fuzzy state aggregation function approximation is tested in two stochastic environments: Tileworld and the simulated robot soccer domain, RoboCup. The Tileworld results demonstrate that a single agent using the combination of FSA and PHC learns quicker and performs better than combined fuzzy state aggregation and Q-learning reinforcement learning alone. Results from the multi-agent RoboCup domain again illustrate that the policy hill climbing algorithms perform better than Q-learning alone in a multi-agent environment. The learning is further enhanced by allowing the agents to share their experience through a weighted strategy sharing.

Download Full-text

Adaptive Fuzzy Function Approximation for Multi-agent Reinforcement Learning

2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology ◽

10.1109/wi-iat.2009.147 ◽

2009 ◽

Cited By ~ 3

Author(s):

Cheng Wu ◽

Waleed Meleis

Keyword(s):

Reinforcement Learning ◽

Function Approximation ◽

Adaptive Fuzzy ◽

Fuzzy Function ◽

Multi Agent

Download Full-text

A solution for the Elevators Group Dispatch by Multiagent Reinforcement Learning

10.5753/eniac.2019.9322 ◽

2019 ◽

Author(s):

Jordão Memória ◽

José Maia

Keyword(s):

Reinforcement Learning ◽

Function Approximation ◽

Value Function ◽

The State ◽

Evaluation Function ◽

State Action ◽

Traffic Pattern ◽

Multiagent Reinforcement Learning ◽

Multi Agent ◽

Action Value

In this work, a modeling and algorithm based on multiagent reinforcement learning is developed for the problem of elevator group dispatch. The main advantage is that, along with the function approximation, this multi-agent solution leads to reduction of the state space, allowing complex states to be addressed with a synthesizing evaluation function. Each elevator is considered an agent that have to decide about two actions: answer or ignore the new call. With some iterations, the agents learn the weights of an evaluation function which approximate the state-action value function. The performance of solution (average waiting time - AWT), shown varying the traffic pattern, flow of people, number of elevators and number of floors, is comparable to other current proposals reported in the literature.

Download Full-text