Java Deep Learning Projects

Notations in reinforcement learning

You may notice that reinforcement learning jargon involves incarnating the algorithm into taking actions in situations to receive rewards. In fact, the algorithm is often referred to as an agent that acts with the environment.

You can just think it is an intelligent hardware agent sensing with sensors and interact with the environment using its actuators. Therefore, it should not be a surprise that much of RL theory is applied in robotics. Now, to prolong our discussion further, we need to know a few terminologies:

• Environment: This is the system having multiple states and mechanisms to transition in between states. For example, for a GridWorld game playing agent's the environment is the grid space itself ...