ViZDoom Competitions: Playing Doom from Pixels

Abstract

This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To play well, the bots needed to understand their surroundings, navigate, explore, and handle the opponents at the same time. These aspects, together with the competitive multi-agent aspect of the game, make the competition a unique platform for evaluating the state of the art reinforcement learning algorithms. The paper discusses the rules, solutions, results, and statistics that give insight into the agents' behaviors. Best-performing agents are described in more detail. The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game. The paper also revisits the ViZDoom environment, which is a flexible, easy to use, and efficient 3D platform for research for vision-based reinforcement learning, based on a well-recognized first-person perspective game Doom.

References in corpus (10)

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• AI2-THOR: An Interactive 3D Environment for Visual AI
• Building Generalizable Agents with a Realistic and Rich 3D Environment
• Neural Map: Structured Memory for Deep Reinforcement Learning
• Gated-Attention Architectures for Task-Oriented Language Grounding
• Neural Episodic Control
• HoME: a Household Multimodal Environment
• CHALET: Cornell House Agent Learning Environment
• Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
• Playing Doom with SLAM-Augmented Deep Reinforcement Learning

Cited by in corpus (13)

• ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
• Self-Supervised Policy Adaptation during Deployment
• Neuroevolution of Self-Interpretable Agents
• Sparse Graphical Memory for Robust Planning
• A Short Survey On Memory Based Reinforcement Learning
• Rotation, Translation, and Cropping for Zero-Shot Generalization
• Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
• Learning to Move with Affordance Maps
• Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning
• Arena: a toolkit for Multi-Agent Reinforcement Learning
• Will GPT-4 Run DOOM?
• Reinforcement Learning with Convolutional Reservoir Computing
• Incremental Scene Synthesis