paper-with-me

Papers

Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint

2021-01-06 · Nithia Vijayan, Prashanth L. A

We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. The first algorithm is a straightforward combination of importance sampling-based off-policy evaluation with SF-based gradient estimation. The second algorithm, inspired by the stochastic variance-reduced gradient (SVRG) algorithm, incorporates variance reduction in the update iteration. For both algorithms, we derive non-asymptotic bounds that establish convergence to an approximate stationary point. From these results, we infer that the first algorithm converges at a rate that is comparable to the well-known REINFORCE algorithm in an off-policy RL context, while the second algorithm exhibits an improved rate of convergence.

📄 PDF Abstract BibTeX arXiv:2101.02137

Code (0)

등록된 구현이 없습니다.

Tasks

Off-policy evaluationReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

Smoothed Action Value Functions for Learning Gaussian Policies

2018-03-06 · ICML 2018 7 · Ofir Nachum, Mohammad Norouzi, George Tucker, Dale Schuurmans

State-action value functions (i.e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning. We propose a new notion of action value defined by a Gaussian s…

continuous-controlContinuous ControlQ-LearningReinforcement Learning+1

Learning Gaussian Policies from Smoothed Action Value Functions

2018-01-01 · ICLR 2018 1 · Ofir Nachum, Mohammad Norouzi, George Tucker, Dale Schuurmans

State-action value functions (i.e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning. We propose a new notion of action value defined by a Gaussian s…

continuous-controlContinuous ControlQ-LearningReinforcement Learning+1

Behavior-Guided Reinforcement Learning

2019-09-25 · Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Anna Choromanska 외

We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing the dual formulation of the WD, we can le…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework

2026-05-11 · Phalguni Nanda, Zaiwei Chen arxiv

In this work, we show that natural policy gradient, a core algorithm in reinforcement learning, admits an exact formulation as a smoothed and averaged form of policy iteration. Specifically, we introduce doubly smoothed …

Reinforcement Learning

Learning to Score Behaviors for Guided Policy Optimization

2019-06-11 · ICML 2020 1 · Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Anna Choromanska 외

We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing the dual formulation of the WD, we can le…

Efficient ExplorationImitation Learningreinforcement-learningReinforcement Learning+1