English
Related papers

Related papers: Is the Bellman residual a bad proxy?

200 papers

In this paper we argue for the fundamental importance of the value distribution: the distribution of the random return received by a reinforcement learning agent. This is in contrast to the common approach to reinforcement learning which…

Machine Learning · Computer Science 2017-07-24 Marc G. Bellemare , Will Dabney , Rémi Munos

The shortcomings of maximum likelihood estimation in the context of model-based reinforcement learning have been highlighted by an increasing number of papers. When the model class is misspecified or has a limited representational capacity,…

Machine Learning · Computer Science 2021-06-08 Evgenii Nikishin , Romina Abachi , Rishabh Agarwal , Pierre-Luc Bacon

We study whether a risk-sensitive objective from asset-pricing theory -- recursive utility -- improves reinforcement learning for portfolio allocation. The Bellman equation under recursive utility involves a certainty equivalent (CE) of…

General Finance · Quantitative Finance 2026-03-25 Minkey Chang

This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our…

Machine Learning · Computer Science 2016-12-02 Nan Jiang , Akshay Krishnamurthy , Alekh Agarwal , John Langford , Robert E. Schapire

Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisit the classical paradigm of Bellman Residual Minimization…

Machine Learning · Computer Science 2025-11-13 Yurun Yuan , Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

Reinforcement learning means finding the optimal course of action in Markovian environments without knowledge of the environment's dynamics. Stochastic optimization algorithms used in the field rely on estimates of the value of a policy.…

Machine Learning · Computer Science 2017-05-25 Leonid Peshkin , Sayan Mukherjee

Reinforcement learning algorithms are generally designed to maximize the expected return across a population. However, a policy that is optimal on average may be suboptimal for certain individuals, leading to potential safety concerns. To…

Machine Learning · Statistics 2026-05-26 Jingyi Li , Peng Wu , Chengchun Shi

Modern deep learning methods provide effective means to learn good representations. However, is a good representation itself sufficient for sample efficient reinforcement learning? This question has largely been studied only with respect to…

Machine Learning · Computer Science 2020-03-02 Simon S. Du , Sham M. Kakade , Ruosong Wang , Lin F. Yang

Although in recent years reinforcement learning has become very popular the number of successful applications to different kinds of operations research problems is rather scarce. Reinforcement learning is based on the well-studied dynamic…

Machine Learning · Computer Science 2020-04-03 Manuel Schneckenreither

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Machine Learning · Computer Science 2023-10-11 Wenzhuo Zhou

Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bilinear programming formulation of value function approximation,…

Artificial Intelligence · Computer Science 2010-06-15 Marek Petrik , Shlomo Zilberstein

Learning models of the environment from data is often viewed as an essential component to building intelligent reinforcement learning (RL) agents. The common practice is to separate the learning of the model from its use, by constructing a…

Machine Learning · Computer Science 2020-11-09 Christopher Grimm , André Barreto , Satinder Singh , David Silver

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-policy sampling and nonlinear function approximation. Many…

Machine Learning · Computer Science 2024-08-02 Andrew Patterson , Adam White , Martha White

In the era of deep reinforcement learning, making progress is more complex, as the collected experience must be compressed into a deep model for future exploitation and sampling. Many papers have shown that training a deep learning policy…

Machine Learning · Computer Science 2025-08-05 Glen Berseth

Empowerment is an information-theoretic method that can be used to intrinsically motivate learning agents. It attempts to maximize an agent's control over the environment by encouraging visiting states with a large number of reachable next…

Machine Learning · Computer Science 2020-01-09 Felix Leibfried , Sergio Pascual-Diaz , Jordi Grau-Moya

In this short note we derive a relationship between the Bregman divergence from the current policy to the optimal policy and the suboptimality of the current value function in a regularized Markov decision process. This result has…

Machine Learning · Computer Science 2022-11-08 Brendan O'Donoghue

Recent policy optimization approaches (Schulman et al., 2015a; 2017) have achieved substantial empirical successes by constructing new proxy optimization objectives. These proxy objectives allow stable and low variance policy learning, but…

Machine Learning · Computer Science 2020-02-24 Marcin B. Tomczak , Dongho Kim , Peter Vrancx , Kee-Eung Kim

Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also…

Machine Learning · Computer Science 2020-07-09 Thomas Spooner , Rahul Savani

Gradient descent or its variants are popular in training neural networks. However, in deep Q-learning with neural network approximation, a type of reinforcement learning, gradient descent (also known as Residual Gradient (RG)) is barely…

Machine Learning · Computer Science 2022-11-15 Shuyu Yin , Tao Luo , Peilin Liu , Zhi-Qin John Xu