Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
Data
Rights / License
Abstract
We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations. We assume that the learner is not allowed to interact with the expert and has no access to reinforcement signal of any kind. Existing inverse reinforcement learning methods come with strong theoretical guarantees, but are computationally expensive, while state-of-the-art policy optimization algorithms achieve significant empirical success, but are hampered by limited theoretical understanding. To bridge the gap between theory and practice, we introduce a novel bilinear saddle-point framework using Lagrangian duality. The proposed primal-dual viewpoint allows us to develop a model-free provably efficient algorithm through the lens of stochastic convex optimization. The method enjoys the advantages of simplicity of implementation, low memory requirements, and computational and sample complexities independent of the number of states. We further present an equivalent no-regret online-learning interpretation.
Permanent link
Publication status
published
Book title
Proceedings of the 38th International Conference on Machine Learning
Journal / series
Volume
139
Pages / Article No.
5257 - 5268
Publisher
PMLR
Event
38th International Conference on Machine Learning (ICML 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
03751 - Lygeros, John / Lygeros, John
Notes
Funding
787845 - Optimal control at large (EC)