In this paper, we consider the problem of low-speed convergence in Reinforcement
Learning (RL). As a solution, various potential-based reward shaping techniques were …

Model-free episodic reinforcement learning problems define the environment reward with
functions that often provide only sparse information throughout the task. Consequently …

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been
actively studied. Unfortunately, this learning type is too slow and difficult to use in practical …

Potential-based reward shaping provides an approach for designing good reward functions,
with the purpose of speeding up learning. However, automatically finding potential functions …

Potential based reward shaping is a powerful technique for accelerating convergence of
reinforcement learning algorithms. Typically, such information includes an estimate of the …

Learning to master human intentions and behave more humanlike is an ultimate goal for
autonomous agents. To achieve that, higher requirements for intelligence are imposed. In …

In this paper, we propose Value Iteration Network for Reward Shaping (VIN-RS), a potential-
based reward shaping mechanism using Convolutional Neural Network (CNN). The …

This paper contributes a preliminary report on the advantages and disadvantages of
incorporating simultaneous human control and feedback signals in the training of a …

In reinforcement learning, reward shaping is an efficient way to guide the learning process of
an agent, as the reward can indicate the optimal policy of the task. The potential-based …

Aside from hand-coded bots, most of the videogame agents rely on experience in one way
or another. Some agents improve over time by adjusting to real experience, while others …