A Nonparametric Off-Policy Policy Gradient
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient algorithms that perform updates using on-policy samples. The price of such inefficiency becomes evident in real-world scenarios such as interaction-driven robot learning, where the success of RL has been rather limited. We address this issue by building on the general sample efficiency of off-policy algorithms. With nonparametric regression and density estimation methods we construct a nonparametric Bellman equation in a principled manner, which allows us to obtain closed-form estimates of the value function, and to analytically express the full policy gradient. We provide a theoretical analysis of our estimate to show that it is consistent under mild smoothness assumptions and empirically show that our approach has better sample efficiency than state-of-the-art policy gradient methods.
Code (1)
Tasks
Density EstimationPolicy Gradient MethodsReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient
Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods eithe…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning
Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a d…
Reinforcement LearningReinforcement Learning with Continuous Actions Under Unmeasured Confounding
This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation wit…
reinforcement-learningReinforcement LearningThe Knowledge Gradient Policy Using A Sparse Additive Belief Model
We propose a sequential learning policy for noisy discrete global optimization and ranking and selection (R\&S) problems with high dimensional sparse belief functions, where there are hundreds or even thousands of featur…
global-optimizationGeneralized Policy Elimination: an efficient algorithm for Nonparametric Contextual Bandits
We propose the Generalized Policy Elimination (GPE) algorithm, an oracle-efficient contextual bandit (CB) algorithm inspired by the Policy Elimination algorithm of \cite{dudik2011}. We prove the first regret optimality g…
Multi-Armed Bandits