Classic meets modern: A pragmatic learning-based congestion control for the internet

S Abbasloo, CY Yen, HJ Chao - … of the Annual conference of the ACM …, 2020 - dl.acm.org
These days, taking the revolutionary approach of using clean-slate learning-based designs
to completely replace the classic congestion control schemes for the Internet is gaining …

Coarse-to-fine q-attention: Efficient learning for visual robotic manipulation via discretisation

S James, K Wada, T Laidlow… - Proceedings of the …, 2022 - openaccess.thecvf.com
We present a coarse-to-fine discretisation method that enables the use of discrete
reinforcement learning approaches in place of unstable and data-inefficient actor-critic …

Auto: Scaling deep reinforcement learning for datacenter-scale automatic traffic optimization

L Chen, J Lingys, K Chen, F Liu - Proceedings of the 2018 conference of …, 2018 - dl.acm.org
Traffic optimizations (TO, eg flow scheduling, load balancing) in datacenters are difficult
online decision-making problems. Previously, they are done with heuristics relying on …

On the effectiveness of fine-tuning versus meta-reinforcement learning

M Zhao, P Abbeel, S James - Advances in neural …, 2022 - proceedings.neurips.cc
Intelligent agents should have the ability to leverage knowledge from previously learned
tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have …

Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning

L Liu, J Hodgins - Acm transactions on graphics (tog), 2018 - dl.acm.org
Basketball is one of the world's most popular sports because of the agility and speed
demonstrated by the players. This agility and speed makes designing controllers to realize …

Learning to schedule control fragments for physics-based characters using deep q-learning

L Liu, J Hodgins - ACM Transactions on Graphics (TOG), 2017 - dl.acm.org
Given a robust control system, physical simulation offers the potential for interactive human
characters that move in realistic and responsive ways. In this article, we describe how to …

Sustaingym: Reinforcement learning environments for sustainable energy systems

C Yeh, V Li, R Datta, J Arroyo… - Advances in …, 2023 - proceedings.neurips.cc
The lack of standardized benchmarks for reinforcement learning (RL) in sustainability
applications has made it difficult to both track progress on specific domains and identify …

Physics-based motion capture imitation with deep reinforcement learning

N Chentanez, M Müller, M Macklin… - Proceedings of the 11th …, 2018 - dl.acm.org
We introduce a deep reinforcement learning method that learns to control articulated
humanoid bodies to imitate given target motions closely when simulated in a physics …

Urban driving with multi-objective deep reinforcement learning

C Li, K Czarnecki - arxiv preprint arxiv:1811.08586, 2018 - arxiv.org
Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should
be able to drive to its destination as fast as possible while avoiding collision, obeying traffic …

Learning hierarchical teaching policies for cooperative agents

DK Kim, M Liu, S Omidshafiei, S Lopez-Cot… - arxiv preprint arxiv …, 2019 - arxiv.org
Collective learning can be greatly enhanced when agents effectively exchange knowledge
with their peers. In particular, recent work studying agents that learn to teach other …