English
Related papers

Related papers: Estimating Q(s,s') with Deep Deterministic Dynamic…

200 papers

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 learn score functions…

Machine Learning · Computer Science 2020-03-05 Aldo Pacchiano , Jack Parker-Holder , Yunhao Tang , Anna Choromanska , Krzysztof Choromanski , Michael I. Jordan

In order to distinguish policies that prescribe good from bad actions in transient states, we need to evaluate the so-called bias of a policy from transient states. However, we observe that most (if not all) works in approximate…

Machine Learning · Computer Science 2022-04-12 Vektor Dewanto , Marcus Gallagher

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations,…

Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic…

Machine Learning · Computer Science 2025-09-30 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…

Machine Learning · Computer Science 2020-09-15 Gabriel Kalweit , Maria Huegle , Moritz Werling , Joschka Boedecker

Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function…

Machine Learning · Computer Science 2023-08-29 Zhendong Wang , Jonathan J Hunt , Mingyuan Zhou

In many practical applications of RL, it is expensive to observe state transitions from the environment. For example, in the problem of plasma control for nuclear fusion, computing the next state for a given state-action pair requires…

Machine Learning · Computer Science 2022-03-16 Viraj Mehta , Biswajit Paria , Jeff Schneider , Stefano Ermon , Willie Neiswanger

We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected return under the…

Machine Learning · Computer Science 2026-05-11 Xiang Li , Nan Jiang

The Quasi Steady-State (QSS) model of long-term dynamics relies on the idea of time-scale decomposition. Assuming that the fast variables are infinitely fast and are stable in the long-term, the QSS model replaces the differential equations…

Systems and Control · Computer Science 2013-10-02 Xiaozhe Wang , Hsiao-Dong Chiang

When predicting a target variable $Y$ from features $X$, the prediction $\hat{Y}$ can be performative: an agent might act on this prediction, affecting the value of $Y$ that we eventually observe. Performative predictions are deliberately…

Machine Learning · Computer Science 2024-04-09 Philip Boeken , Onno Zoeter , Joris M. Mooij

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-09-10 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value…

Machine Learning · Computer Science 2019-07-02 Ahmed Touati , Harsh Satija , Joshua Romoff , Joelle Pineau , Pascal Vincent

It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have…

Machine Learning · Computer Science 2019-06-11 Luke Metz , Julian Ibarz , Navdeep Jaitly , James Davidson

Transfer learning of prediction models has been extensively studied, while the corresponding policy learning approaches are rarely discussed. In this paper, we propose principled approaches for learning the optimal policy in the target…

Machine Learning · Computer Science 2025-05-20 Xueqing Liu , Qinwei Yang , Zhaoqing Tian , Ruocheng Guo , Peng Wu

Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution based on history trajectory and target returns for each…

Machine Learning · Computer Science 2024-05-28 Shengchao Hu , Ziqing Fan , Chaoqin Huang , Li Shen , Ya Zhang , Yanfeng Wang , Dacheng Tao

Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of…

Artificial Intelligence · Computer Science 2013-01-30 Richard Dearden , Nir Friedman , David Andre

A temporally abstract action, or an option, is specified by a policy and a termination condition: the policy guides option behavior, and the termination condition roughly determines its length. Generally, learning with longer options (like…

Artificial Intelligence · Computer Science 2017-12-05 Anna Harutyunyan , Peter Vrancx , Pierre-Luc Bacon , Doina Precup , Ann Nowe

An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we…

Machine Learning · Computer Science 2024-06-27 Jacob Adamczyk , Volodymyr Makarenko , Stas Tiomkin , Rahul V. Kulkarni

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This…

Machine Learning · Computer Science 2024-09-13 Zahra Shahrooei , Ali Baheri

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the…

Machine Learning · Computer Science 2019-06-17 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar