You've been logged out of GDC Vault since the maximum users allowed for this account has been reached. To access Members Only content on GDC Vault, please log out of GDC Vault from the computer which last accessed this account.

Click here to find out about GDC Vault Membership options for more users.

close

Session Name:

Imitation Learning: Building Practical Agents to Test and Explore a First-Person Shooter

Overview:

The talk introduces style-centric autoplay agents that game developers can train quickly and on a budget to facilitate testing and evaluating the gameplay of a title under development. The focus on the practical and stylistic aspects suggests a simple approach based on the Markov model. Markov agents are trainable interactively and can incorporate new game features without re-training the entire model. While such agents efficiently capture the demonstrated gameplay style, they may require fallback heuristics to address possible lack of performance, or the game states not explicitly present in organic play-throughs. Imitation learning on the data bootstrapped from the enhanced with heuristics Markov agent allows training of a compact computationally efficient DNN model suitable for automated game evaluation and testing. A generic First-Person Shooter game example provides a practical context for the presentation. The GitHub repository illustrates Markov agents in more detail and uses OpenAI gym environments for an interactive demo.

Did you know free users get access to 30% of content from the last 2 years?


Get your team full access to the most up to date GDC content

  • GDC Summer 2020
  • Igor Borovikov
  • EA
  • free content
  • Programming
  • Programming