Fast deep reinforcement learning using online adjustments from the past

2018-10-18 · NeurIPS 2018 12 · Steven Hansen, Pablo Sprechmann, Alexander Pritzel, André Barreto, Charles Blundell

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVAis performant on a demonstration task and Atari games.

📄 PDF Abstract BibTeX arXiv:1810.08163

Code (2)

AnnaNikitaRL/EVA pytorch

deepmind/open_spiel

Tasks

Atari GamesDeep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Retrieval

Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning

2024-05-26 · Aneesh Muppidi, ZhiYu Zhang, Heng Yang

A key challenge in lifelong reinforcement learning (RL) is the loss of plasticity, where previous learning progress hinders an agent's adaptation to new tasks. While regularization and resetting can help, they require pr…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

The fundamental representation of pricing adjustments

2025-03-19 · Benedict Burnett, Ryan McCrickerd, Benjamin Piau

This article consolidates and extends past work on derivative pricing adjustments, including XVA, by providing an encapsulating representation of the adjustment between any two derivative pricing functions, within an Ito…

Provably Efficient Causal Reinforcement Learning with Confounded Observational Data

2020-06-22 · NeurIPS 2021 12 · Lingxiao Wang, Zhuoran Yang, Zhaoran Wang

Empowered by expressive function approximators such as neural networks, deep reinforcement learning (DRL) achieves tremendous empirical successes. However, learning expressive function approximators requires collecting a…

Autonomous Driving Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

PVBF: A Framework for Mitigating Parameter Variation Imbalance in Online Continual Learning

2025-02-25 · Zelin Tao, Hao Deng, Mingqing Liu, Lijun Zhang 외

Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored pa…

Continual Learning

Distributed Online Service Coordination Using Deep Reinforcement Learning

2021-07-07 · Stefan Schneider, Haydar Qarawlus, Holger Karl

Services often consist of multiple chained components such as microservices in a service mesh, or machine learning functions in a pipeline. Providing these services requires online coordination including scaling the serv…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2