Learning to Survive using Reinforcement Learning with MLAgents

Abstract

Listen

Translate article

Abstract: Simulations have been there for a long time, in different versions and level of complexity. Training a Reinforcement Learning model in a 3D environment lets us understand a lot of new insights from the inference. There have been some examples where the AI learns to Feed Itself, Learns to Start walking, jumping etc. The reason one trains an entire model from the agent knowing nothing to being a perfect task achiever is that during the process, new behavioral patterns can be recorded. Reinforcement Learning is a feedback-based Machine Learning technique in which an agent learns how to behave in a given environment by performing actions and observing the outcomes of those actions. For each positive action, the agent receives positive feedback; for each negative action, the agent receives negative feedback or a penalty. A general simple agent would learn to perform a task and get some reward on accomplishing it. The Agent is also given punishment if it does something that it’s not supposed to do. These simple simulations can evolve, try to use their surroundings, try to fight with other agents to accomplish their goal