English
Related papers

Related papers: LLQL: Logistic Likelihood Q-Learning for Reinforce…

200 papers

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a…

This paper develops an online inverse reinforcement learning algorithm aimed at efficiently recovering a reward function from ongoing observations of an agent's actions. To reduce the computation time and storage space in reward estimation,…

Robotics · Computer Science 2017-08-01 Kun Li , Joel W. Burdick

Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several crucial applications in the real world, such as drug discovery,…

Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased…

Machine Learning · Computer Science 2023-12-06 Taehyun Cho , Seungyub Han , Heesoo Lee , Kyungjae Lee , Jungwoo Lee

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…

Machine Learning · Computer Science 2022-10-19 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

We describe a new approach for managing aleatoric uncertainty in the Reinforcement Learning (RL) paradigm. Instead of selecting actions according to a single statistic, we propose a distributional method based on the second-order stochastic…

Machine Learning · Computer Science 2020-10-08 John D. Martin , Michal Lyskawinski , Xiaohu Li , Brendan Englot

Deep reinforcement learning (RL) has shown remarkable success in specific offline decision-making scenarios, yet its theoretical guarantees are still under development. Existing works on offline RL theory primarily emphasize a few trivial…

Machine Learning · Computer Science 2023-12-20 Di Wu , Yuling Jiao , Li Shen , Haizhao Yang , Xiliang Lu

Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions,…

Computation and Language · Computer Science 2026-05-12 Yao Du , Shanshan Song , Xiaomeng Li

To better align Large Language Models (LLMs) with human judgment, Reinforcement Learning from Human Feedback (RLHF) learns a reward model and then optimizes it using regularized RL. Recently, direct alignment methods were introduced to…

We propose a new algorithm for model-based distributional reinforcement learning (RL), and prove that it is minimax-optimal for approximating return distributions with a generative model (up to logarithmic factors), resolving an open…

Machine Learning · Computer Science 2024-11-05 Mark Rowland , Li Kevin Wenliang , Rémi Munos , Clare Lyle , Yunhao Tang , Will Dabney

Reinforcement learning (RL) post-training is crucial for LLM alignment and reasoning, but existing policy-based methods, such as PPO and DPO, can fall short of fixing shortcuts inherited from pre-training. In this work, we introduce…

Machine Learning · Computer Science 2025-10-21 Jin Peng Zhou , Kaiwen Wang , Jonathan Chang , Zhaolin Gao , Nathan Kallus , Kilian Q. Weinberger , Kianté Brantley , Wen Sun

Function approximation has been an indispensable component in modern reinforcement learning algorithms designed to tackle problems with large state spaces in high dimensions. This paper reviews recent results on error analysis for these…

Machine Learning · Computer Science 2024-02-27 Jihao Long , Jiequn Han

Classical reinforcement learning (RL) techniques are generally concerned with the design of decision-making policies driven by the maximisation of the expected outcome. Nevertheless, this approach does not take into consideration the…

Machine Learning · Computer Science 2023-01-02 Thibaut Théate , Damien Ernst

Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes. RAML incorporates…

Machine Learning · Computer Science 2017-10-31 Xuezhe Ma , Pengcheng Yin , Jingzhou Liu , Graham Neubig , Eduard Hovy

Traditional reinforcement learning (RL) assumes the agents make decisions based on Markov decision processes (MDPs) with one-step transition models. In many real-world applications, such as energy management and stock investment, agents can…

Machine Learning · Computer Science 2025-10-22 Chenbei Lu , Zaiwei Chen , Tongxin Li , Chenye Wu , Adam Wierman

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward:…

Machine Learning · Statistics 2025-12-09 Denis Belomestny , Alexey Naumov , Sergey Samsonov

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

We consider the problem of Reinforcement Learning for nonlinear stochastic dynamical systems. We show that in the RL setting, there is an inherent ``Curse of Variance" in addition to Bellman's infamous ``Curse of Dimensionality", in…

Machine Learning · Computer Science 2021-07-30 Raman Goyal , Suman Chakravorty , Ran Wang , Mohamed Naveed Gul Mohamed

This work handles the inverse reinforcement learning (IRL) problem where only a small number of demonstrations are available from a demonstrator for each high-dimensional task, insufficient to estimate an accurate reward function. Observing…

Artificial Intelligence · Computer Science 2017-10-16 Kun Li , Joel W. Burdick

Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and…

Machine Learning · Computer Science 2023-04-19 Andrew Patterson , Victor Liao , Martha White