Selecting Subgoals using Deep Learning in Minecraft: A Preliminary Report
نویسندگان
چکیده
Deep learning is a powerful tool for labeling images in computer vision. We apply deep learning to select subgoals in the simulated game environment of Minecraft. Prior work showed that subgoal selection could be learned with off-the-shelf machine learning techniques and full state knowledge. We extend that work to learn subgoal selection from raw pixels. In a limited pilot study where a virtual chracter must overcome obstacles, we show that AlexNet can learn an effective policy 93% of the time with very little training.
منابع مشابه
A Deep Hierarchical Approach to Lifelong Learning in Minecraft
The ability to reuse or transfer knowledge from one task to another in lifelong learning problems, such as Minecraft, is one of the major challenges faced in AI. Reusing knowledge across tasks is crucial to solving tasks efficiently with lower sample complexity. We provide a Reinforcement Learning agent with the ability to transfer knowledge by learning reusable skills, a type of temporally ext...
متن کاملModular Multitask Reinforcement Learning with Policy Sketches
We describe a framework for multitask deep reinforcement learning guided by policy sketches. Sketches annotate each task with a sequence of named subtasks, providing high-level structural relationships among tasks, but not providing the detailed guidance required by previous work on learning policy abstractions for RL (e.g. intermediate rewards, subtask completion signals, or intrinsic motivati...
متن کاملDeep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft
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 frame...
متن کاملExplore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds
We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy m...
متن کاملFrom Wooden Blocks and Lego to Minecraft: Designing and Playing with Blocks to Learn in a 3D Virtual World
Minecraft, a virtual 3D world game to fight nighttime monsters and a design environment for building shelters, strikes a balance between “want to” and “have to” participate, that is, students “want to” use it (self-directed learning) and educators can impose constraints by knowledge (curriculumdriven learning). These two goals often seen as contradictory are reconciled by taking advantage of th...
متن کامل