Search Results for author:
Found 7 papers, 4 papers with code
Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL
In this paper, we provide a mathematical characterization of this phenomenon, which we refer to as policy confounding, and show, through a series of examples, when and how it occurs in practice.
Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning.
Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL).
Online Planning in POMDPs with Self-Improving Simulators
To plan reliably and efficiently while the approximate simulator is learning, we develop a method that adaptively decides which simulator to use for every simulation, based on a statistic that measures the accuracy of the approximate simulator.
Offline Contextual Bandits for Wireless Network Optimization
The explosion in mobile data traffic together with the ever-increasing expectations for higher quality of service call for the development of AI algorithms for wireless network optimization.
Influence-Augmented Online Planning for Complex Environments
In this work, we propose influence-augmented online planning, a principled method to transform a factored simulator of the entire environment into a local simulator that samples only the state variables that are most relevant to the observation and reward of the planning agent and captures the incoming influence from the rest of the environment using machine learning methods.
Influence-aware Memory Architectures for Deep Reinforcement Learning
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally.
