Oct 16, 2020 · We propose an auto-tuning technique based on the ELBO for self-supervised reinforcement learning. Our approach can auto-tune three hyperparameters.

Our approach can auto-tune three hyperparameters: the replay buffer size, the number of policy gradient updates during each epoch, and the number of exploration ...

Mar 8, 2021 · Experiments show that our method can auto-tune online and yields the best performance at a fraction of the time and computational resources.

This work proposes an auto-tuning technique based on the Evidence Lower Bound for self-supervised reinforcement learning that can auto-tune three ...

Oct 29, 2020 · Policy optimization in reinforcement learning requires the selection of numerous hyperparameters across different environments.

Our approach can auto-tune three hyperparameters: the replay buffer size, the number of policy gradient updates during each epoch, and the number of exploration ...

Workshop: Deep Reinforcement Learning. Poster: Hyperparameter Auto-tuning in Self-Supervised Robotic Learning. Abstract: It appears you are a search engine ...

Dec 6, 2020 · Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes ...

我们的方法可以自动调整三个超参数：重放缓冲区大小、每个历元期间策略梯度更新的数量以及每个历元中探索步骤的数量。我们使用最先进的自监督机器人学习框架（使用Soft ...

Bibliographic details on Hyperparameter Auto-tuning in Self-Supervised Robotic Learning.