Alexandre Pichard
Alexandre Pichard has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Shmakov
Hewlett Packard Enterprise USA
2 shared publications - Ashwin Ramesh Babu
Hewlett Packard Enterprise
2 shared publications - Avisek Naug
Hewlett Packard Enterprise 820 N McCarthy Blvd 95035 Milpitas CA USA
2 shared publications - Mathieu Cocho
Carnegie Clean Energy Australia
2 shared publications - Sahand Ghorbanpour
Hewlett Packard Enterprise
2 shared publications - Soumyendu Sarkar
Hewlett Packard Enterprise
2 shared publications
Latest Publications
- Open Access
Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves
The industrial multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices in challenging circumstances need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. The Multi-Agent Reinforcement Learning (MARL) controller trained with the Proximal Policy Optimization (PPO) algorithm can handle these complexities. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics and find that they are key to better performance. We investigated the performance of a fully connected neural network (FCN), LSTM, and Transformer model variants with varying depths and gated residual connections. Our results show that the transformer model of moderate depth with gated residual connections around the multi-head attention, multi-layer perceptron, and the transformer block (STrXL) proposed in this paper is optimal and boosts energy efficiency by an average of 22.1% for these complex spread waves over the existing spring damper (SD) controller. Furthermore, unlike the default SD controller, the transformer controller almost eliminated the mechanical stress from the rotational yaw motion for angled waves. Demo: https://tinyurl.com/yueda3jh
Open AccessFunction Approximation for Reinforcement Learning Controller for Energy from Spread Waves
The industrial multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices in challenging circumstances need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. The Multi-Agent Reinforcement Learning (MARL) controller trained with the Proximal Policy Optimization (PPO) algorithm can handle these complexities. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics and find that they are key to better performance. We investigated the performance of a fully connected neural network (FCN), LSTM, and Transformer model variants with varying depths and gated residual connections. Our results show that the transformer model of moderate depth with gated residual connections around the multi-head attention, multi-layer perceptron, and the transformer block (STrXL) proposed in this paper is optimal and boosts energy efficiency by an average of 22.1% for these complex spread waves over the existing spring damper (SD) controller. Furthermore, unlike the default SD controller, the transformer controller almost eliminated the mechanical stress from the rotational yaw motion for angled waves. Demo: https://tinyurl.com/yueda3jh
- Open Access
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 6, 6201-6209
Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves
Electronic proceedings of IJCAI 2023
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 6, 6201-6209
Open AccessFunction Approximation for Reinforcement Learning Controller for Energy from Spread Waves
Electronic proceedings of IJCAI 2023