English
Related papers

Related papers: Bridging the Gap Between Average and Discounted TD…

200 papers

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

It is still common to use Q-learning and temporal difference (TD) learning-even though they have divergence issues and sound Gradient TD alternatives exist-because divergence seems rare and they typically perform well. However, recent work…

Machine Learning · Computer Science 2020-09-21 Sina Ghiassian , Andrew Patterson , Shivam Garg , Dhawal Gupta , Adam White , Martha White

Reinforcement learning (RL) algorithms typically optimize the expected cumulative reward, i.e., the expected value of the sum of scalar rewards an agent receives over the course of a trajectory. The expected value averages the performance…

Machine Learning · Computer Science 2025-09-01 Xinyi Sheng , Dominik Baumann

Reinforcement Learning (RL) remains a central optimisation framework in machine learning. Although RL agents can converge to optimal solutions, the definition of ``optimality'' depends on the environment's statistical properties. The…

Machine Learning · Computer Science 2026-01-14 Bert Verbruggen , Arne Vanhoyweghen , Vincent Ginis

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer,…

Machine Learning · Computer Science 2020-07-07 Ron Amit , Ron Meir , Kamil Ciosek

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…

Machine Learning · Computer Science 2026-01-26 Chengyang Ying , Xinning Zhou , Zhongkai Hao , Hang Su , Songming Liu , Dong Yan , Jun Zhu

Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions. However, when dealing with extended timescales, discounting…

Machine Learning · Computer Science 2019-11-21 Akshay Dharmavaram , Matthew Riemer , Shalabh Bhatnagar

We present an optimistic Q-learning algorithm for regret minimization in average reward reinforcement learning under an additional assumption on the underlying MDP that for all policies, the time to visit some frequent state $s_0$ is finite…

Machine Learning · Computer Science 2025-06-17 Priyank Agrawal , Shipra Agrawal

TD($\lambda$) in value-based MARL algorithms or the Temporal Difference critic learning in Actor-Critic-based (AC-based) algorithms synergistically integrate elements from Monte-Carlo simulation and Q function bootstrapping via dynamic…

Machine Learning · Computer Science 2026-05-13 Yue Deng , Zirui Wang , Yin Zhang

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation,…

Artificial Intelligence · Computer Science 2025-02-11 Jiachen Xi , Alfredo Garcia , Petar Momcilovic

The interaction between an artificial agent and its environment is bi-directional. The agent extracts relevant information from the environment, and affects the environment by its actions in return to accumulate high expected reward.…

Systems and Control · Computer Science 2018-06-06 Stas Tiomkin , Naftali Tishby

We consider a general class of non-linear Bellman equations. These open up a design space of algorithms that have interesting properties, which has two potential advantages. First, we can perhaps better model natural phenomena. For…

Machine Learning · Computer Science 2019-07-09 Hado van Hasselt , John Quan , Matteo Hessel , Zhongwen Xu , Diana Borsa , Andre Barreto

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning. Despite these…

The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, LTL has the downside that it is sensitive to small…

Logic in Computer Science · Computer Science 2023-05-31 Rajeev Alur , Osbert Bastani , Kishor Jothimurugan , Mateo Perez , Fabio Somenzi , Ashutosh Trivedi

Reinforcement learning has been successful across several applications in which agents have to learn to act in environments with sparse feedback. However, despite this empirical success there is still a lack of theoretical understanding of…

Machine Learning · Statistics 2023-11-08 Blake Bordelon , Paul Masset , Henry Kuo , Cengiz Pehlevan

We derive uniform all-time concentration bound of the type 'for all $n \geq n_0$ for some $n_0$' for TD(0) with linear function approximation. We work with online TD learning with samples from a single sample path of the underlying Markov…

Machine Learning · Computer Science 2026-01-13 Siddharth Chandak , Vivek S. Borkar

One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key…

Artificial Intelligence · Computer Science 2016-10-25 Martha White , Adam White

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

Machine Learning · Computer Science 2026-03-05 Debamita Ghosh , George K. Atia , Yue Wang

Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary covariance correction, and TDRC further regularizes this correction in a single-timescale…

Artificial Intelligence · Computer Science 2026-05-29 Xingguo Chen , Zhiang He , Yuchen Shen , Shangdong Yang , Chao Li , Guang Yang , Wenhao Wang

While there are convergence guarantees for temporal difference (TD) learning when using linear function approximators, the situation for nonlinear models is far less understood, and divergent examples are known. Here we take a first step…

Machine Learning · Computer Science 2020-02-12 David Brandfonbrener , Joan Bruna