conftrace_

2024 JMLR JMLR 2024

Policy Gradient Methods in the Presence of Symmetries and State Abstractions

Abstract

Prakash Panangaden, Sahand Rezaei-Shoshtari, Rosie Zhao, David Meger, Doina Precup; 25(71):1−57, 2024.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Prakash Panangaden, Sahand Rezaei-Shoshtari, Rosie Zhao, David Meger, Doina Precup

Topics

Artificial Intelligence > Core AI > Planning Machine Learning > Core Methods > Representation Learning Reinforcement Learning > Methods > Policy Learning Artificial Intelligence > Core AI > Reasoning

Keywords

state abstraction policy gradient continuous control

More from JMLR 2024

All JMLR 2024 papers →

Learnability of Linear Port-Hamiltonian Systems

Tangential Wasserstein Projections

Scaling Instruction-Finetuned Language Models

Pareto Smoothed Importance Sampling

Data Summarization via Bilevel Optimization

Differentially private methods for managing model uncertainty in linear regression