Prioritizing Pass Options by Reinforcement of Simulated Soccer Agents
ثبت نشده
چکیده
Learning to act and cooperate in dynamic multi-agent environments can be an excessively complex task, especially when it comes to imitating natural biological multi-agent systems (MAS). RoboCup simulated soccer is a multi-agent environment which presents many challenges to cooperative learning algorithms, including a large state space, hidden and uncertain states, multiple heterogeneous independent agents learning simultaneously, and long and variable delays in effects of actions. A semi-markov decision process (SMDP) is recited for the episodic task of simulated soccer playing agents by learning pass option priorities through residual Sarsa(λ) with variable λ and Multi-Layer Perceptrons (MLP) as function approximator. It is concluded that having a correct multi-criterion reward/punishment strategy can greatly help to form the desired emergent
منابع مشابه
An Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کاملReinforcement Learning for RoboCup Soccer Keepaway
RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple independent agents learning simultaneously, and long and variable delays in the effects of actions. We describe our application of episodic SMDP Sarsa(λ) with linear tile-coding function approximation and variable λ to learning higher-level dec...
متن کاملScaling Reinforcement Learning toward RoboCup Soccer
RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the e ects of actions. We describe our application of episodic SMDP Sarsa( ) with linear tile-coding function approximation and variable to learning higher-level decisions in a keepaway subtask of RoboCup...
متن کاملLearning complementary multiagent behaviors: a case study
As machine learning is applied to increasingly complex tasks, it is likely that the diverse challenges encountered can only be addressed by combining the strengths of different learning algorithms. We examine this aspect of learning through a case study grounded in the robot soccer context. The task we consider is Keepaway, a popular benchmark for multiagent reinforcement learning from the simu...
متن کاملA Two Pass Learning Algorithm for Simulated Soccer
Reinforcement learning (RL) is an effective machine learning paradigm, but because the state space cardinality often grows exponentially as the dimensionality grows linearly, many domains are not well-suited for traditional RL techniques. Tile coding with linear function approximation has been widely used to circumvent the curse of dimensionality, but suffers from the drawback that trial and er...
متن کامل