2024年度 人工知能学会全国大会（第38回）
2024年5月28日〜5月31日アクトシティ浜松＋オンライン
2024年度 人工知能学会全国大会（第38回）
2024年5月28日〜5月31日アクトシティ浜松＋オンライン
[3Q5-IS-2b-04]Generative Model of Policies: Exploring the Latent Space with Human Feedback
〇Raffael Bolla Di Lorenzo1, Michita Imai1(1. Keio University)
Reinforcement learning often makes use of training a population of agents with a diversity of behaviors. A population of agents can be used to train a robust agent, that can for instance cooperate with a human partner, or simply discover many ways to solve a given task.
Generative Models of Policies are able to discover a wide range of agent policies that succeed at a given task without requiring separate policy parameters. Moreover, they can adapt to new tasks or goals simply by optimizing in the learnt latent space of policies.
In this paper, we focus on the understanding and the exploration of the latent space of policies for discovering new behaviors. More specifically, we take inspiration from StyleGAN's mapping network to better structure the latent space. We then design an exploration protocol that uses human feedback to discover new behaviors.
Generative Models of Policies are able to discover a wide range of agent policies that succeed at a given task without requiring separate policy parameters. Moreover, they can adapt to new tasks or goals simply by optimizing in the learnt latent space of policies.
In this paper, we focus on the understanding and the exploration of the latent space of policies for discovering new behaviors. More specifically, we take inspiration from StyleGAN's mapping network to better structure the latent space. We then design an exploration protocol that uses human feedback to discover new behaviors.