• Corpus ID: 3246939

A Guided Genetic Algorithm for the Planning in Lunar Lander Games

  title={A Guided Genetic Algorithm for the Planning in Lunar Lander Games},
  author={Zhangbo Liu},
We propose a guided genetic algorithm (GA) for planning in games. In guided GA, an extra reinforcement component is inserted into the evolution procedure of GA. During each evolution procedure, the reinforcement component will simulate the execution of a series of actions of an individual before the real trial and adjust the series of actions according to the reinforcement thus try to improve the performance. We then apply it to a Lunar Lander game in which the falling lunar module needs to… 

Figures from this paper


A greedy genetic algorithm for the quadratic assignment problem
The overall performance of the GA for the QAP improves by using greedy methods but not their overuse, and the use of several possible enhancements to GAs are investigated and illustrated using the Quadratic Assignment Problem, one of the hardest nut in the field of combinatorial optimization.
The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces
Parti-game is a new algorithm for learning feasible trajectories to goal regions in high dimensional continuous state-spaces and applies techniques from game-theory and computational geometry to efficiently and adaptively concentrate high resolution only on critical areas.
A study of reinforcement learning for the robot with many degrees of freedom - acquisition of locomotion patterns for multi-legged robot
  • Kazuyuki Ito, F. Matsuno
  • Computer Science
    Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292)
  • 2002
A new reinforcement learning algorithm: Q-learning with dynamic structuring of exploration space based on genetic algorithm applicable to systems with high dimensional action and interior state spaces, for example, a robot with many redundant degrees of freedom is presented.
Self-improving reactive agents based on reinforcement learning, planning and teaching
This paper compares eight reinforcement learning frameworks: Adaptive heuristic critic (AHC) learning due to Sutton, Q-learning due to Watkins, and three extensions to both basic methods for speeding up learning and two extensions are experience replay, learning action models for planning, and teaching.
AI Techniques for Game Programming
AI Techniques for Game Programming takes the difficult topics of genetic algorithms and neural networks and explains them in plain English, and shows you how to train a network to recognize mouse gestures and use state-of-the-art techniques for creating neural networks with dynamic topologies.
Controlling chaos by GA-based reinforcement learning neural network
This paper proposes a TD (temporal difference) and GA (genetic algorithm) based reinforcement (TDGAR) neural learning scheme for controlling chaotic dynamical systems based on the technique of small
Practical Reinforcement Learning in Continuous Spaces
This paper introduces an algorithm that safely approximates the value function for continuous state control tasks, and that learns quickly from a small amount of data, and gives experimental results using this algorithm to learn policies for both a simulated task and also for a real robot, operating in an unaltered environment.
A self-learning fuzzy logic controller using genetic algorithms with reinforcements
In this paper, the adaptive heuristic critic algorithm of Barto et al. (1987) is extended to include a priori control knowledge of human operators and it is shown that the system can solve more concretely a fairly difficult control learning problem.
Combination of online clustering and Q-value based GA for reinforcement fuzzy system design
This paper proposes a combination of online clustering and Q-value based genetic algorithm (GA) learning scheme for fuzzy system design (CQGAF) with reinforcements. The CQGAF fulfills GA-based fuzzy
Reinforcement Learning: A Survey
Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.