Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft
By Stephan Alaniz. 2018
16 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Sergey Levine
- Yoshua Bengio
- Quoc V. Le
- Jianfeng Gao
- Kyunghyun Cho
- Jason Aaron Edward Weston
- Ruslan Salakhutdinov
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
- Bernt Schiele
- Ming-Hsuan Yang
- Cordelia Schmid
In Reinforcement Learning
- Sergey Levine
- Chelsea Finn
- Pieter Abbeel
- George Tucker
- Shixiang Shane Gu
- Ofir Nachum
- Aviral Kumar
- Arthur Szlam
Citations in the corpus
- Model-Based Reinforcement Learning for Atari (2019, background): “…several recent works have incorporated images into real-world (Finn et al., 2016; Finn & Levine, 2017; Babaeizadeh et al., 2017a; Ebert et al., 2017; Piergiovanni et al., 2018; Paxton et al., 2019; Rybkin et al., 2018; Ebert et al., 2018) and simulated (Watter et al., 2015; Hafner et al., 2019) .”
- Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks (2018, methodology): “Also closely related is the approach from Alaniz [33] attaining impressive results by combining model-based learning with planning in the visual domain of Minecraft.”
- Why Build an Assistant in Minecraft? (2019, methodology): “It is often used as a testbed for ML model architectures trained using reinforcement learning methods, e.g. [71, 85, 3, 66, 82].”
- Model-Based Stabilisation of Deep Reinforcement Learning (2018, result): “One exception is the preliminary work of (Alaniz 2017) obtaining impressive results in Minecraft with Monte Carlo tree search.”