In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing number of inactive neurons, thereby …
P Christodoulou - arXiv preprint arXiv:1910.07207, 2019 - arxiv.org
Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve …
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer …
Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of …
J Wu, Z Huang, C Lv - IEEE Transactions on Intelligent Vehicles, 2022 - ieeexplore.ieee.org
To further improve learning efficiency and performance of reinforcement learning (RL), a novel uncertainty-aware model-based RL method is proposed and validated in autonomous …
YH Wu, X Wang, M Hamaya - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT …
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this …
Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states …
Model efficiency is a critical aspect of developing and deploying machine learning models. Inference time and latency directly affect the user experience, and some applications have …