Deep reinforcement learning (DRL) has achieved great successes in many simulated tasks.
Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user.
In this paper, we proposed a deep interactive reinforcement learning method for path following of AUV by combining the advantages of deep reinforcement learning and interactive RL.
Our results show that learning from demonstration can allow a TAMER agent to learn a roughly optimal policy up to the deepest search and encourage the agent to explore along the optimal path.
Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning.