Project MineRL: Sample efficient reinforcement learning using human prior Introduction A challenge to develop a system to obtain a diamond in Minecraft using limited amount of training time. Since the task is super hard, the organizers also created a smaller problems like chopping trees, navigate to a point, obtain an iron pickaxe. In this post I am going to share my experience about solving the navigate to a point problem. For those who don’t know what Minecraft is, let me tell you about it briefly. Minecraft is a sandbox game with a 3D world in a block structure. Every object in the game is made from combination of sqaure blocks. I suggest you take a quick look at the game trailer on youtube here to get an idea what the game is about.

Deep Q-learning We introduce deep neural networks to do the Q-Learning, hence the name Deep Q-Learning. Instead of calculating Q-values for each state-action pair, we calculate Q-values for all actions given the state and then select the action with maximum q-value. This concept was first introduced in Playing Atari with Deep Reinforcement Learning paper. The authors show that they were able to surpass human experts on three out of seven Atari games tested using deep neural networks to solve these reinforcement problems.

Introduction Reinforcement learning is a type of machine learning problem which is solved using the past experiences and interactions of the agent with the world. In other words, Reinforcement learning is mappings of situations with the available actions to maximize a numerical reward signal. Usually rewards are positive if the action taken is desirable and negative if the action is undesirable. The agent is never told which action to take or which action is optimal for a given situation, but instead it must discover on its own which actions to take that would yield maximum reward. In many cases the action taken for a given situation may affect not only immediate reward but also the next situation and may have consequences on future rewards. These characteristics of trial and error search and delayed rewards are distinguishing features of reinforcement learning.