English
Related papers

Related papers: Variance Penalized On-Policy and Off-Policy Actor-…

200 papers

Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves multiple tasks at the same time. This paper presents a constrained formulation for multi-task RL where the goal is to maximize the average…

Optimization and Control · Mathematics 2024-05-07 Sihan Zeng , Thinh T. Doan , Justin Romberg

We study policy gradient for mean-field control in continuous time in a reinforcement learning setting. By considering randomised policies with entropy regularisation, we derive a gradient expectation representation of the value function,…

Machine Learning · Statistics 2023-03-14 Noufel Frikha , Maximilien Germain , Mathieu Laurière , Huyên Pham , Xuanye Song

In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSAC) algorithm, which…

Machine Learning · Computer Science 2021-06-14 Jingliang Duan , Yang Guan , Shengbo Eben Li , Yangang Ren , Bo Cheng

This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms. First, we formulate off-policy RL as a stochastic proximal point iteration. The target network plays the role of the variable of…

Machine Learning · Computer Science 2020-08-04 Marco Maggipinto , Gian Antonio Susto , Pratik Chaudhari

Offline reinforcement learning, wherein one uses off-policy data logged by a fixed behavior policy to evaluate and learn new policies, is crucial in applications where experimentation is limited such as medicine. We study the estimation of…

Machine Learning · Computer Science 2020-06-09 Nathan Kallus , Masatoshi Uehara

Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to…

Machine Learning · Computer Science 2022-04-05 Ling Pan , Longbo Huang , Tengyu Ma , Huazhe Xu

Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability…

Artificial Intelligence · Computer Science 2019-02-08 Hélène Plisnier , Denis Steckelmacher , Diederik M. Roijers , Ann Nowé

Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our…

Machine Learning · Computer Science 2020-01-22 Juan Vargas , Lazar Andjelic , Amir Barati Farimani

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Machine Learning · Computer Science 2020-08-12 Omer Gottesman , Joseph Futoma , Yao Liu , Sonali Parbhoo , Leo Anthony Celi , Emma Brunskill , Finale Doshi-Velez

A central challenge to applying many off-policy reinforcement learning algorithms to real world problems is the variance introduced by importance sampling. In off-policy learning, the agent learns about a different policy than the one being…

Machine Learning · Computer Science 2022-06-20 Eric Graves , Sina Ghiassian

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

In many real-world multi-agent cooperative tasks, due to high cost and risk, agents cannot continuously interact with the environment and collect experiences during learning, but have to learn from offline datasets. However, the transition…

Machine Learning · Computer Science 2023-08-01 Jiechuan Jiang , Zongqing Lu

This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving,…

Machine Learning · Computer Science 2018-11-08 Sina Ghiassian , Andrew Patterson , Martha White , Richard S. Sutton , Adam White

Traditional continuous deep reinforcement learning (RL) algorithms employ deterministic or unimodal Gaussian actors, which cannot express complex multimodal decision distributions. This limitation can hinder their performance in…

Machine Learning · Computer Science 2025-11-04 Ziqi Wang , Jiashun Liu , Ling Pan

The intersection of causal inference and machine learning for decision-making is rapidly expanding, but the default decision criterion remains an \textit{average} of individual causal outcomes across a population. In practice, various…

Machine Learning · Computer Science 2022-11-08 Wenshuo Guo , Michael I. Jordan , Angela Zhou

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL…

Machine Learning · Computer Science 2021-09-28 Zhaorun Chen , Binhao Chen , Shenghan Xie , Liang Gong , Chengliang Liu , Zhengfeng Zhang , Junping Zhang

Motivated by applications in risk-sensitive reinforcement learning, we study mean-variance optimization in a discounted reward Markov Decision Process (MDP). Specifically, we analyze a Temporal Difference (TD) learning algorithm with linear…

Machine Learning · Computer Science 2025-03-13 Tejaram Sangadi , L. A. Prashanth , Krishna Jagannathan

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…

Machine Learning · Computer Science 2019-04-09 Ishan Durugkar , Matthew Hausknecht , Adith Swaminathan , Patrick MacAlpine

We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. Our motivation comes from recent work on off-policy Proximal Policy Optimization (PPO), which improves training stability, sampling…

Value-based algorithms are a cornerstone of off-policy reinforcement learning due to their simplicity and training stability. However, their use has traditionally been restricted to discrete action spaces, as they rely on estimating…

Machine Learning · Computer Science 2025-10-23 Yigit Korkmaz , Urvi Bhuwania , Ayush Jain , Erdem Bıyık