English
Related papers

Related papers: Off-OAB: Off-Policy Policy Gradient Method with Op…

200 papers

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision…

Machine Learning · Computer Science 2025-12-23 Brett Daley , Martha White , Christopher Amato , Marlos C. Machado

We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions…

Machine Learning · Computer Science 2026-03-19 Yihong Guo , Yu Yang , Pan Xu , Anqi Liu

A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms. In this…

Machine Learning · Computer Science 2020-07-31 Mark Rowland , Will Dabney , Rémi Munos

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance…

Artificial Intelligence · Computer Science 2018-06-26 Daniel S. Brown , Scott Niekum

Traditional on-policy Reinforcement Learning with Verifiable Rewards (RLVR) frameworks suffer from experience waste and reward homogeneity, which directly hinders learning efficiency on difficult samples during large language models…

Artificial Intelligence · Computer Science 2026-03-17 Xu Wan , Yansheng Wang , Wenqi Huang , Mingyang Sun

Traditional reinforcement learning lacks the ability to provide stability guarantees. More recent algorithms learn Lyapunov functions alongside the control policies to ensure stable learning. However, the current self-learned Lyapunov…

Systems and Control · Electrical Eng. & Systems 2026-01-19 Sarvan Gill , Daniela Constantinescu

In offline reinforcement learning, the challenge of out-of-distribution (OOD) is pronounced. To address this, existing methods often constrain the learned policy through policy regularization. However, these methods often suffer from the…

Machine Learning · Computer Science 2024-07-16 Tenglong Liu , Yang Li , Yixing Lan , Hao Gao , Wei Pan , Xin Xu

Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy…

Machine Learning · Computer Science 2026-03-10 Mai Pham , Vikrant Vaze , Peter Chin

We study the efficient off-policy evaluation of natural stochastic policies, which are defined in terms of deviations from the behavior policy. This is a departure from the literature on off-policy evaluation where most work consider the…

Machine Learning · Computer Science 2020-11-05 Nathan Kallus , Masatoshi Uehara

Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that learning a good policy is difficult in a domain where…

Machine Learning · Computer Science 2019-06-27 Takahisa Imagawa , Takuya Hiraoka , Yoshimasa Tsuruoka

Off-policy evaluation (OPE) is the method that attempts to estimate the performance of decision making policies using historical data generated by different policies without conducting costly online A/B tests. Accurate OPE is essential in…

Artificial Intelligence · Computer Science 2021-09-20 Yuta Saito , Takuma Udagawa , Kei Tateno

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility $f(J_1^\pi,\dots,J_M^\pi)$ over multiple objectives, where each $J_m^\pi$ denotes the expected discounted…

Machine Learning · Computer Science 2026-03-10 Swetha Ganesh , Vaneet Aggarwal

Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge: \textit{policy lag}, which is the mismatch between the…

Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face significant challenges due to high variance and poor…

Machine Learning · Computer Science 2025-06-10 Armin Behnamnia , Gholamali Aminian , Alireza Aghaei , Chengchun Shi , Vincent Y. F. Tan , Hamid R. Rabiee

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Many practical applications, such as recommender systems and learning to rank, involve solving multiple similar tasks. One example is learning of recommendation policies for users with similar movie preferences, where the users may still…

Machine Learning · Computer Science 2022-12-12 Joey Hong , Branislav Kveton , Sumeet Katariya , Manzil Zaheer , Mohammad Ghavamzadeh

Recent advances of gradient temporal-difference methods allow to learn off-policy multiple value functions in parallel with- out sacrificing convergence guarantees or computational efficiency. This opens up new possibilities for sound…

Artificial Intelligence · Computer Science 2014-05-22 Anna Harutyunyan , Tim Brys , Peter Vrancx , Ann Nowe

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($\pi$) and the behavior policy (b) is a major cause…

‹ Prev 1 8 9 10 Next ›