English
Related papers

Related papers: In Hindsight: A Smooth Reward for Steady Explorati…

200 papers

Future reward estimation is a core component of reinforcement learning agents; i.e., Q-value and state-value functions, predicting an agent's sum of future rewards. Their scalar output, however, obfuscates when or what individual future…

Artificial Intelligence · Computer Science 2024-08-16 Mark Towers , Yali Du , Christopher Freeman , Timothy J. Norman

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to…

Machine Learning · Computer Science 2019-05-16 Chen Huang , Shuangfei Zhai , Walter Talbott , Miguel Angel Bautista , Shih-Yu Sun , Carlos Guestrin , Josh Susskind

We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are…

Machine Learning · Computer Science 2022-11-11 John D. Co-Reyes , Yingjie Miao , Daiyi Peng , Esteban Real , Sergey Levine , Quoc V. Le , Honglak Lee , Aleksandra Faust

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Theoretical Economics · Economics 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

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

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which…

Machine Learning · Computer Science 2024-09-18 S. R. Eshwar , Mayank Motwani , Nibedita Roy , Gugan Thoppe

In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the TD error is defined by a bootstrap method, its computation tends to be noisy and destabilize…

Machine Learning · Computer Science 2026-04-03 Taisuke Kobayashi

In reinforcement learning, Return, which is the weighted accumulated future rewards, and Value, which is the expected return, serve as the objective that guides the learning of the policy. In classic RL, return is defined as the…

Machine Learning · Computer Science 2020-10-27 Yufei Wang , Qiwei Ye , Tie-Yan Liu

Positive affect has been linked to increased interest, curiosity and satisfaction in human learning. In reinforcement learning, extrinsic rewards are often sparse and difficult to define, intrinsically motivated learning can help address…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Dean Zadok , Daniel McDuff , Ashish Kapoor

We study deep reinforcement learning (RL) algorithms with delayed rewards. In many real-world tasks, instant rewards are often not readily accessible or even defined immediately after the agent performs actions. In this work, we first…

Machine Learning · Computer Science 2021-06-23 Beining Han , Zhizhou Ren , Zuofan Wu , Yuan Zhou , Jian Peng

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To address this, some methods propose replaying data from previous…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Chenyang Wang , Junjun Jiang , Xingyu Hu , Xianming Liu , Xiangyang Ji

In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The…

Machine Learning · Computer Science 2019-05-16 Borislav Mavrin , Shangtong Zhang , Hengshuai Yao , Linglong Kong , Kaiwen Wu , Yaoliang Yu

Robot control using reinforcement learning has become popular, but its learning process generally terminates halfway through an episode for safety and time-saving reasons. This study addresses the problem of the most popular exception…

Robotics · Computer Science 2026-02-25 Taisuke Kobayashi

Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during that episode but does not affect the dynamics. Various…

Machine Learning · Computer Science 2023-03-09 Alexander Levine , Soheil Feizi

We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for online reward estimation. Instead of relying on fixed heuristics, our method recursively…

Machine Learning · Computer Science 2026-04-28 Zixuan Xia , Quanxi Li

Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged…

Machine Learning · Computer Science 2020-11-05 Nino Vieillard , Olivier Pietquin , Matthieu Geist

Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error…

Machine Learning · Computer Science 2021-02-08 Ang A. Li , Zongqing Lu , Chenglin Miao

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

This paper investigates estimating the variance of a temporal-difference learning agent's update target. Most reinforcement learning methods use an estimate of the value function, which captures how good it is for the agent to be in a…

Artificial Intelligence · Computer Science 2018-02-15 Craig Sherstan , Brendan Bennett , Kenny Young , Dylan R. Ashley , Adam White , Martha White , Richard S. Sutton

We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control problems with linear dynamics but unknown coefficients and…

Machine Learning · Computer Science 2021-12-22 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang