English
Related papers

Related papers: From Importance Sampling to Doubly Robust Policy G…

200 papers

Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy…

Machine Learning · Computer Science 2021-10-12 Osbert Bastani

The off-policy paradigm casts recommendation as a counterfactual decision-making task, allowing practitioners to unbiasedly estimate online metrics using offline data. This leads to effective evaluation metrics, as well as learning…

Machine Learning · Computer Science 2024-09-17 Olivier Jeunen , Aleksei Ustimenko

Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not…

Machine Learning · Computer Science 2018-06-25 Yasuhiro Fujita , Shin-ichi Maeda

We study the evaluation of a policy under best- and worst-case perturbations to a Markov decision process (MDP), using transition observations from the original MDP, whether they are generated under the same or a different policy. This is…

Artificial Intelligence · Computer Science 2024-11-05 Andrew Bennett , Nathan Kallus , Miruna Oprescu , Wen Sun , Kaiwen Wang

Standard policy gradients weight each sampled action by advantage alone, regardless of how likely that action was under the current policy. This creates two pathologies: within a single decision context (e.g. one image or prompt), a rare…

Machine Learning · Computer Science 2026-03-17 Ian Osband

Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot…

Machine Learning · Computer Science 2019-09-10 Wenjie Shi , Shiji Song , Cheng Wu

The doubly-robust (DR) estimator is popular for evaluating causal effects in observational studies and is often perceived as more desirable than inverse probability weighting (IPW) or outcome modeling alone because it provides extra…

Methodology · Statistics 2026-02-03 Chengxin Yang , Laine E. Thomas , Fan Li

This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we…

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we…

Machine Learning · Computer Science 2019-11-14 Qingpeng Cai , Ling Pan , Pingzhong Tang

We introduce data structures for solving robust regression through stochastic gradient descent (SGD) by sampling gradients with probability proportional to their norm, i.e., importance sampling. Although SGD is widely used for large scale…

Machine Learning · Computer Science 2022-07-19 Sepideh Mahabadi , David P. Woodruff , Samson Zhou

Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. It is critical in a number of sequential decision making problems ranging from healthcare…

Machine Learning · Statistics 2023-01-02 Yang Xu , Chengchun Shi , Shikai Luo , Lan Wang , Rui Song

We introduce Group Policy Gradient (GPG), a family of critic-free policy-gradient estimators for general MDPs. Inspired by the success of GRPO's approach in Reinforcement Learning from Human Feedback (RLHF), GPG replaces a learned value…

Machine Learning · Computer Science 2025-10-07 Junhua Chen , Zixi Zhang , Hantao Zhong , Rika Antonova

Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recently introduced direct alignment methods, which are often…

Policy gradient methods have become a standard for training reinforcement learning agents in a scalable and efficient manner. However, they do not account for transition uncertainty, whereas learning robust policies can be computationally…

Machine Learning · Computer Science 2023-12-12 Navdeep Kumar , Esther Derman , Matthieu Geist , Kfir Levy , Shie Mannor

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e.…

Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when…

Machine Learning · Computer Science 2021-09-15 Simon P. Shen , Yecheng Jason Ma , Omer Gottesman , Finale Doshi-Velez

Hybrid RL is the setting where an RL agent has access to both offline data and online data by interacting with the real-world environment. In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method…

Machine Learning · Computer Science 2023-11-15 Yifei Zhou , Ayush Sekhari , Yuda Song , Wen Sun

In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data. Consequently, tackling bias has emerged as a major challenge in the field of recommendation systems.…

Information Retrieval · Computer Science 2023-08-21 ZiJie Song , JiaWei Chen , Sheng Zhou , QiHao Shi , Yan Feng , Chun Chen , Can Wang

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

Machine Learning · Computer Science 2024-07-30 Jayesh Singla , Ananye Agarwal , Deepak Pathak

In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require any large batches. Specifically, we propose a fast…

Machine Learning · Computer Science 2020-08-07 Feihu Huang , Shangqian Gao , Jian Pei , Heng Huang