9 papers
Dynamics Models for Offline Hyperparameter Selection in Real-World RL
Jordan Coblin, Han Wang, Martha White +1
A key obstacle to deploying reinforcement learning in real-world systems is hyperparameter selection, particularly when simulators are unavailable and online experimentation is cos…
Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners
Haseeb Shah, Lingwei Zhu, Adam White +1
Reinforcement learning is increasingly being considered for controlling real-world systems, from fusion plasma and autonomous vehicles to drug discovery and drinking water treatmen…
Revisiting Mixture Policies in Entropy-Regularized Actor-Critic
Jiamin He, Samuel Neumann, Jincheng Mei +2
Mixture policies theoretically offer greater flexibility than unimodal policies in continuous action reinforcement learning, but the practical benefits of this complexity remain el…
Forager: a lightweight testbed for continual learning with partial observability in RL
Steven Tang, Xinze Xiong, Anna Hakhverdyan +7
In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have…
Gradient Iterated Temporal-Difference Learning
Théo Vincent, Kevin Gerhardt, Yogesh Tripathi +5
Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update…
Deep Reinforcement Learning with Gradient Eligibility Traces
Esraa Elelimy, Brett Daley, Andrew Patterson +3
Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for t…
GVFs in the Real World: Making Predictions Online for Water Treatment
Muhammad Kamran Janjua, Haseeb Shah, Martha White +3
In this paper we investigate the use of reinforcement-learning based prediction approaches for a real drinking-water treatment plant. Developing such a prediction system is a criti…
Harnessing Discrete Representations For Continual Reinforcement Learning
Edan Meyer, Adam White, Marlos C. Machado
Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations.…
AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning
Subhojeet Pramanik, Esraa Elelimy, Marlos C. Machado +1
In this paper we investigate transformer architectures designed for partially observable online reinforcement learning. The self-attention mechanism in the transformer architecture…