English
Related papers

Related papers: Why Policy Gradient Algorithms Work for Undiscount…

200 papers

We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve…

Machine Learning · Computer Science 2018-05-01 Rein Houthooft , Richard Y. Chen , Phillip Isola , Bradly C. Stadie , Filip Wolski , Jonathan Ho , Pieter Abbeel

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

Machine Learning · Computer Science 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

We present the first finite-sample analysis of policy evaluation in robust average-reward Markov Decision Processes (MDPs). Prior work in this setting have established only asymptotic convergence guarantees, leaving open the question of…

Machine Learning · Statistics 2025-12-11 Yang Xu , Washim Uddin Mondal , Vaneet Aggarwal

Policy-based algorithms are among the most widely adopted techniques in model-free RL, thanks to their strong theoretical groundings and good properties in continuous action spaces. Unfortunately, these methods require precise and…

Machine Learning · Computer Science 2023-06-14 Luca Sabbioni , Francesco Corda , Marcello Restelli

Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. However, these methods suffer from high sample complexity and instability issues. In this paper, we address these challenges by providing…

Machine Learning · Computer Science 2021-03-17 Yannis Flet-Berliac , Reda Ouhamma , Odalric-Ambrym Maillard , Philippe Preux

In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent…

Machine Learning · Computer Science 2024-06-27 Jeongyeol Kwon , Shie Mannor , Constantine Caramanis , Yonathan Efroni

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

Machine Learning · Computer Science 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon…

Optimization and Control · Mathematics 2025-10-16 Dongsheng Ding , Kaiqing Zhang , Jiali Duan , Tamer Başar , Mihailo R. Jovanović

Policy gradient (PG) is a reinforcement learning (RL) approach that optimizes a parameterized policy model for an expected return using gradient ascent. While PG can work well even in non-Markovian environments, it may encounter plateaus or…

Machine Learning · Computer Science 2024-07-08 Tetsuro Morimura , Kazuhiro Ota , Kenshi Abe , Peinan Zhang

Risk-averse total-reward Markov Decision Processes (MDPs) offer a promising framework for modeling and solving undiscounted infinite-horizon objectives. Existing model-based algorithms for risk measures like the entropic risk measure (ERM)…

Machine Learning · Computer Science 2025-10-27 Xihong Su , Jia Lin Hau , Gersi Doko , Kishan Panaganti , Marek Petrik

In this work, we study $\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs) and introduce a framework called dynamic policy gradient (DynPG). The framework directly integrates dynamic programming with (any) policy…

Machine Learning · Computer Science 2024-11-08 Sara Klein , Xiangyuan Zhang , Tamer Başar , Simon Weissmann , Leif Döring

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…

Distributional Reinforcement Learning (RL) maintains the entire probability distribution of the reward-to-go, i.e. the return, providing more learning signals that account for the uncertainty associated with policy performance, which may be…

Machine Learning · Computer Science 2021-03-24 Luchen Li , A. Aldo Faisal

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between…

Artificial Intelligence · Computer Science 2017-12-11 Li Zhou , Kevin Small , Oleg Rokhlenko , Charles Elkan

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

Machine Learning · Computer Science 2022-10-17 Ashish Kumar Jayant , Shalabh Bhatnagar

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…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In…

Machine Learning · Computer Science 2022-05-25 Prashanth L. A. , Michael Fu

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Machine Learning · Computer Science 2026-02-04 Xiangxiang Chu , Hailang Huang , Xiao Zhang , Fei Wei , Yong Wang

Algorithms developed under stationary Markov Decision Processes (MDPs) often face challenges in non-stationary environments, and infinite-horizon formulations may not directly apply to finite-horizon tasks. To address these limitations, we…

Machine Learning · Computer Science 2025-12-03 Zhizuo Chen , Theodore T. Allen