Autonomous inter-task transfer in reinforcement learning do245

Agents, physical and virtual entities that interact with theirenvironment, are becoming increasingly prevalent. How-ever, if agents are to behave intelligently in complex, dynamic, and noisy environments, we believe that they must be able to learn and adapt. The reinforcement learning (RL) par-adigm is a popular way for such agents to learn from experience with minimal feedback. One of the central questions in RL is how best to generalize knowledge to successfully learn and adapt. In reinforcement learning problems, agents sequentially observe their state and execute actions. The goal is to maximize a real-valued reward signal, which may be time delayed. For example, an agent could learn to play a game by being told what the state of the board is, what the legal actions are, and then whether it wins or loses at the end of the game. However, unlike in supervised learning scenarios, the agent is never provided the “correct ” action. Instead, the agent can only gather data by interacting with an environment, receiving information about the results, its actions, and the reward signal. RL is often used because of the framework’s flexibility and due to the develop-ment of increasingly data-efficient algorithms. RL agents learn by interacting with the environment, gather-ing data. If the agent is virtual and acts in a simulated environ-ment, training data can be collected at the expense of comput-er time. However, if the agent is physical, or the agent must act on a “real-world ” problem where the online reward is critical, such data can be expensive. For instance, a physical robot will degrade over time and must be replaced, and an agent learning to automate a company’s operations may lose money while training. When RL agents begin learning tabula rasa, mastering difficult tasks may be infeasible, as they require significant amounts of data even when using state-of-the-art RL approach-es. There are many contemporary approaches to speed up “vanilla ” RL methods. Transfer learning (TL) is one such tech-nique. Transfer learning is an umbrella term used when knowledge i