A Neuroevolution Approach to General Atari Game Playing

@article{Hausknecht2014ANA,
  title={A Neuroevolution Approach to General Atari Game Playing},
  author={Matthew J. Hausknecht and Joel Lehman and Risto Miikkulainen and Peter Stone},
  journal={IEEE Transactions on Computational Intelligence and AI in Games},
  year={2014},
  volume={6},
  pages={355-366}
}
This paper addresses the challenge of learning to play many different video games with little domain-specific knowledge. Specifically, it introduces a neuroevolution approach to general Atari 2600 game playing. Four neuroevolution algorithms were paired with three different state representations and evaluated on a set of 61 Atari games. The neuroevolution agents represent different points along the spectrum of algorithmic sophistication - including weight evolution on topologically fixed neural… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 70 CITATIONS, ESTIMATED 30% COVERAGE

Emergent Solutions to High-Dimensional Multitask Reinforcement Learning

  • Evolutionary Computation
  • 2018
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Neuroevolution in Games: State of the Art and Open Challenges

  • IEEE Transactions on Computational Intelligence and AI in Games
  • 2017
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Comparative Analysis of Existing Architectures for General Game Agents

  • 2015 17th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)
  • 2015
VIEW 13 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Emergent Tangled Graph Representations for Atari Game Playing Agents

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 8 Highly Influenced Citations

  • Averaged 17 Citations per year over the last 3 years

  • 31% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 48 REFERENCES

Similar Papers

Loading similar papers…