English
Related papers

Related papers: RUDDER: Return Decomposition for Delayed Rewards

200 papers

We consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting. In contrast to discrete-time MDPs, a continuous-time process moves to a state and stays there for a…

Machine Learning · Computer Science 2024-07-03 Xuefeng Gao , Xun Yu Zhou

Markov decision processes (MDPs) are widely used in modeling decision making problems in stochastic environments. However, precise specification of the reward functions in MDPs is often very difficult. Recent approaches have focused on…

Artificial Intelligence · Computer Science 2012-02-20 Eunsoo Oh , Kee-Eung Kim

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

Machine Learning · Computer Science 2017-01-11 Tanmay Shankar , Santosha K. Dwivedy , Prithwijit Guha

Reinforcement learning algorithms typically assume rewards to be sampled from light-tailed distributions, such as Gaussian or bounded. However, a wide variety of real-world systems generate rewards that follow heavy-tailed distributions. We…

Machine Learning · Computer Science 2021-02-26 Vincent Zhuang , Yanan Sui

We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining…

Artificial Intelligence · Computer Science 2020-06-24 Juergen Schmidhuber

Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors),…

Machine Learning · Computer Science 2020-02-04 Jingkang Wang , Yang Liu , Bo Li

This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that…

Machine Learning · Computer Science 2025-09-09 Laixi Shi , Gen Li , Yuting Wei , Yuxin Chen , Matthieu Geist , Yuejie Chi

Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to adjust the performance of AI agents to meet human…

Machine Learning · Computer Science 2025-06-23 Tsunehiko Tanaka , Kenshi Abe , Kaito Ariu , Tetsuro Morimura , Edgar Simo-Serra

The goal of reinforcement learning is estimating a policy that maps states to actions and maximizes the cumulative reward of a Markov Decision Process (MDP). This is oftentimes achieved by estimating first the optimal (reward) value…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing…

Artificial Intelligence · Computer Science 2019-12-06 Maor Gaon , Ronen I. Brafman

Regular decision processes (RDPs) are a subclass of non-Markovian decision processes where the transition and reward functions are guarded by some regular property of the past (a lookback). While RDPs enable intuitive and succinct…

Logic in Computer Science · Computer Science 2023-12-15 Ernst Moritz Hahn , Mateo Perez , Sven Schewe , Fabio Somenzi , Ashutosh Trivedi , Dominik Wojtczak

This paper offers a new hybrid probably approximately correct (PAC) reinforcement learning (RL) algorithm for Markov decision processes (MDPs) that intelligently maintains favorable features of its parents. The designed algorithm, referred…

Machine Learning · Computer Science 2021-01-29 Ashkan Zehfroosh , Herbert G. Tanner

Policy optimization is a widely-used method in reinforcement learning. Due to its local-search nature, however, theoretical guarantees on global optimality often rely on extra assumptions on the Markov Decision Processes (MDPs) that bypass…

Machine Learning · Computer Science 2021-07-20 Haipeng Luo , Chen-Yu Wei , Chung-Wei Lee

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it…

Machine Learning · Computer Science 2020-06-09 Zihan Zhang , Yuan Zhou , Xiangyang Ji

This paper describes an improvement in Deep Q-learning called Reverse Experience Replay (also RER) that solves the problem of sparse rewards and helps to deal with reward maximizing tasks by sampling transitions successively in reverse…

Machine Learning · Computer Science 2019-10-24 Egor Rotinov

Q-learning is a popular Reinforcement Learning (RL) algorithm which is widely used in practice with function approximation (Mnih et al., 2015). In contrast, existing theoretical results are pessimistic about Q-learning. For example, (Baird,…

Machine Learning · Computer Science 2021-10-20 Naman Agarwal , Syomantak Chaudhuri , Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

Machine Learning · Computer Science 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

Motivated by applications to online advertising and recommender systems, we consider a game-theoretic model with delayed rewards and asynchronous, payoff-based feedback. In contrast to previous work on delayed multi-armed bandits, we focus…

Computer Science and Game Theory · Computer Science 2020-06-22 Amélie Héliou , Panayotis Mertikopoulos , Zhengyuan Zhou

We introduce a new framework of episodic tabular Markov decision processes (MDPs) with adversarial preferences, which we refer to as preference-based MDPs (PbMDPs). Unlike standard episodic MDPs with adversarial losses, where the numerical…

Machine Learning · Computer Science 2025-07-17 Taira Tsuchiya , Shinji Ito , Haipeng Luo

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true…

Machine Learning · Computer Science 2026-05-13 Nadav Timor , Ravid Shwartz-Ziv , Micah Goldblum , Yann LeCun , David Harel