IGN : Implicit Generative Networks

Abstract

In this work, we build recent advances in distributional reinforcement learning to give a state-of-art distributional variant of the model based on the IQN. We achieve this by using the GAN model's generator and discriminator function with the quantile regression to approximate the full quantile value for the state-action return distribution. We demonstrate improved performance on our baseline dataset - 57 Atari 2600 games in the ALE. Also, we use our algorithm to show the state-of-art training performance of risk-sensitive policies in Atari games with the policy optimization and evaluation.

2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Generative Adversarial Networks
• Distributed Distributional Deterministic Policy Gradients
• Implicit Quantile Networks for Distributional Reinforcement Learning
• On the Sample Complexity of Reinforcement Learning with a Generative Model
• Statistical analysis of Wasserstein GANs with applications to time series forecasting
• MBGDT:Robust Mini-Batch Gradient Descent