The Malmo Platform for Artificial Intelligence Experimentation

By Matthew Johnson, Katja Hofmann, Tim Hutton, David Bignell. 2016

423 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

ShapeWorld - A new test methodology for multimodal language understanding (2017, methodology): “Various platforms following this paradigm have been released, mostly aimed at reinforcement learning: the Arcade Learning Environment / Atari 2600 games (Bellemare et al., 2013), OpenAI Gym (Brockman et al., 2016), DeepMind Lab (Beattie et al., 2016), Project Malmo (Johnson et al., 2016), to name a ”
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents (2017, background): “This is the case in Minecraft (Project Malmo; Johnson et al., 2016), Starcraft (Ontañón et al., 2013), and robotic RL platforms (Sutton et al., 2011).”
Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning (2017, methodology): “Figure 3 (left) shows the two room environment in Minecraft that we created using the Malmo platform (Johnson et al., 2016).”
Continual Reinforcement Learning in 3D Non-stationary Environments (2019, background): “VizDoom [20], followed soon after by other research platforms like DeepMind Labs [4] and Malmo [17], allowed researchers to start exploring new interesting research directions with the aim of scaling up current reinforcement learning algorithms.”
Information-Theoretic Considerations in Batch Reinforcement Learning (2019, background): “One of the prominent examples where such a condition holds is inspired by “visual gridworld” environments in empirical RL research (see e.g., Johnson et al., 2016): the dynamics are deﬁned over a small number of hidden states (e.g., grids), and the agent receives high dimensional observations that…”
TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games (2016, methodology): “To provide the community with useful research environments, work was done towards building platforms based on videogames such as Torcs [27], Mario AI [20], Unreal’s BotPrize [10], the Atari Learning Environment [3], VizDoom [12], and Minecraft [11], all of which have allowed researchers to train dee”
MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence (2017, methodology): “However, existing experimentation platforms, including ALE (Bellemare et al. 2013), OpenAI Gym/Universe (Brockman et al. 2016), Malmo (Johnson et al. 2016), ELF (Tian et al. 2017) and SC2LE (Vinyals et al. 2017) fail to meet the demand.”
AI2-THOR: An Interactive 3D Environment for Visual AI (2017, background): “UETorch [14], Project Malmo [12], and SceneNet [11] are other examples of non-photo-realistic simulated environments.”
Target-driven visual navigation in indoor scenes using deep reinforcement learning (2016, methodology): “Similar frameworks have been proposed by [39], [40], [44], [42], [41], but the”
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (2018, methodology): “[2017] to render 10,000 Minecraft scenes, building upon the Malmo interface [Johnson et al., 2016].”
DeepMind Lab (2016, methodology): “Among 3D platforms for AI research, DeepMind Lab is comparable to others like VizDoom (Kempka et al., 2016) and Minecraft (Johnson et al., 2016; Tessler et al., 2016).”
Dopamine: A Research Framework for Deep Reinforcement Learning (2018, background): “…conclusions extend to similar environments, including continuous control (Duan et al., 2016; Tassa et al., 2018), ﬁrst-person environments (Kempka et al., 2016; Beattie et al., 2016; Johnson et al., 2016), and to some extent real-time strategy games (Tian et al., 2017; Vinyals et al., 2017).”
Learning to Speak and Act in a Fantasy Text Adventure Game (2019, background): “…et al., 2017), MINOS (Savva et al., 2017), Matterport3D (Chang et al., 2017) and AI2-THOR (Kolve et al., 2017), and the Minecraft MALMO project (Johnson et al., 2016), but they typically are suited to reinforcement learning of actions, and involve templated language for navigation or question…”
Building Generalizable Agents with a Realistic and Rich 3D Environment (2018, background): “, 2016) and Malmo (Johnson et al., 2016)), real-time strategy decision (TorchCraft (Synnaeve et al.”
A Survey of Reinforcement Learning Informed by Natural Language (2019, background): “Another option is presented by open-world video games like Minecraft [Johnson et al., 2016], in which users are free to assemble complex structures from simple parts, and thus have an essentially unlimited universe of possible objects to describe and goals involving those objects.”
MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments (2017, background): “Simulator Agent Modalities Framerate Environment Dataset size Gazebo articulated sensor 10s+ FPS indoor few environments (Koenig and Howard, 2014) plugins + outdoor Project Malmo continuous color 10s+ FPS Minecraft few environments (Johnson et al., 2016) /discrete ViZDoom continuous color, depth, se”
Interactive Fiction Games: A Colossal Adventure (2019, background): “2016), and Malmo (Johnson et al. 2016), IF games stress natural language understanding and commonsense reasoning, and feature combinatorial action spaces.”
A Brief Survey of Deep Reinforcement Learning (2017, neutral): “exposed an interface to the Minecraft sandbox game [44].”
Avalanche: an End-to-End Library for Continual Learning (2021, background): “Other relevant projects in the ﬁeld of reinforcement learning are Dopamine [5], which focuses on simplicity and easy prototyping, and project Malmo [24], which is based on the famous Minecraft game.”