← Back to papers
2020 IJCAI IJCAI 2020

Generalized Representation Learning Methods for Deep Reinforcement Learning

Abstract

Deep reinforcement learning (DRL) increases the successful applications of reinforcement learning (RL) techniques but also brings challenges such as low sample efficiency. In this work, I propose generalized representation learning methods to obtain compact state space suitable for RL from a raw observation state. I expect my new methods will increase sample efficiency of RL by understandable representations of state and therefore improve the performance of RL.

🌉 Interdisciplinary Bridge — Machine Learning and Reinforcement Learning
🧭 Keyword Pioneer — compact state space
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio

Authors

Hanhua Zhu

Topics

Machine Learning > Core Methods > Representation Learning Reinforcement Learning > Methods > Deep RL Machine Learning > Learning Paradigms > Multi-Task Learning Deep Learning > Learning Types > Reinforcement Learning Deep Learning > Learning Types > Representation Learning

Keywords

deep reinforcement learning representation learning sample efficiency state representation compact state space observation state
Download PDF

Related papers

Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization 2020
Intention Progression under Uncertainty 2020
Almost Group Envy-free Allocation of Indivisible Goods and Chores 2020
Uniform Welfare Guarantees Under Identical Subadditive Valuations 2020
Biased Opinion Dynamics: When the Devil is in the Details 2020