• A
  • A
  • A
  • АБB
  • АБB
  • АБB
  • А
  • А
  • А
  • А
  • А
Обычная версия сайта

Глава

Deep Reinforcement Learning with VizDoom First-Person Shooter

P. 3-17.
Dmitry Akimov, Makarov I.

In this work, we study deep reinforcement algorithms for partially observable Markov decision processes (POMDP) combined with Deep Q-Networks. To our knowledge, we are the first to apply standard Markov decision process architectures to POMDP scenarios. We propose an extension of DQN with Dueling Networks and several other model-free policies to training agent using deep reinforcement learning in VizDoom environment, which is replication of Doom first-person shooter. We develop several agents for the following scenarios in VizDoom first-person shooter (FPS): Basic, Defend The Center, Health Gathering. We compare our agent with Recurrent DQN with Prioritized Experience Replay and Snapshot Ensembling agent and get approximately triple increase in per episode reward. It is important to say that POMDP scenario close the gap between human and computer player scenarios thus providing more meaningful justification for Deep RL agent performance.