Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft

Abstract

Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model predicts the next frame and the rewards one step ahead given the last four frames of the agent's first-person-view image and the current action. Then a Monte Carlo tree search algorithm uses this model to plan the best sequence of actions for the agent to perform. On the proposed task in Minecraft, our model-based approach reaches the performance comparable to the Deep Q-Network's, but learns faster and, thus, is more training sample efficient.

arXiv commentThe 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2017

References in corpus (1)

• Control of Memory, Active Perception, and Action in Minecraft

Cited by in corpus (6)

• Model-Based Reinforcement Learning for Atari
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• CraftAssist: A Framework for Dialogue-enabled Interactive Agents
• Why Build an Assistant in Minecraft?
• CraftAssist Instruction Parsing: Semantic Parsing for a Minecraft Assistant
• Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks