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 …
M Klissarov, D Precup - Advances in Neural Information …, 2020 - proceedings.neurips.cc
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 …
Y Chen, L Schomaker, F Cruz - arXiv preprint arXiv:2402.04581, 2024 - arxiv.org
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 …
M Dann, F Zambetta… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
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 …