English
Related papers

Related papers: Policy Optimization with Sparse Global Contrastive…

200 papers

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a…

Machine Learning · Computer Science 2020-12-16 Haotian Fu , Hongyao Tang , Jianye Hao , Chen Chen , Xidong Feng , Dong Li , Wulong Liu

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

Machine Learning · Computer Science 2021-09-29 Hamed Khorasgani , Haiyan Wang , Chetan Gupta , Susumu Serita

Modern deep reinforcement learning (RL) algorithms are motivated by either the generalised policy iteration (GPI) or trust-region learning (TRL) frameworks. However, algorithms that strictly respect these theoretical frameworks have proven…

Machine Learning · Computer Science 2024-11-21 Jakub Grudzien Kuba , Christian Schroeder de Witt , Jakob Foerster

Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent the agent's policies using neural networks, making their…

Artificial Intelligence · Computer Science 2024-09-10 Jasmina Gajcin , Jovan Jeromela , Ivana Dusparic

Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Group Relative Policy Optimization (GRPO). However, GRPO-style RL methods in multi-domain…

Computation and Language · Computer Science 2026-05-26 Zongji Yu , Wenshui Luo , Yiliu Sun , Hao Fang , Runmin Cong , Chaochao Lu , Chen Gong

Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…

Machine Learning · Computer Science 2025-09-12 Somnath Hazra , Pallab Dasgupta , Soumyajit Dey

Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Chaoyang Wang , Zeyu Zhang , Meng Meng , Xu Zhou , Haiyun Jiang

While current benchmark reinforcement learning (RL) tasks have been useful to drive progress in the field, they are in many ways poor substitutes for learning with real-world data. By testing increasingly complex RL algorithms on…

Machine Learning · Computer Science 2018-11-16 Amy Zhang , Yuxin Wu , Joelle Pineau

Reinforcement Learning (RL) has shown great promise in domains like healthcare and robotics but often struggles with adoption due to its lack of interpretability. Counterfactual explanations, which address "what if" scenarios, provide a…

Machine Learning · Computer Science 2025-05-20 Shuyang Dong , Shangtong Zhang , Lu Feng

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Machine Learning · Computer Science 2021-06-03 Sindhu Padakandla

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

Traditionally, Reinforcement Learning (RL) aims at deciding how to act optimally for an artificial agent. We argue that deciding when to act is equally important. As humans, we drift from default, instinctive or memorized behaviors to…

Machine Learning · Computer Science 2022-03-17 Alexis Jacq , Johan Ferret , Olivier Pietquin , Matthieu Geist

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

We propose a reinforcement learning (RL) framework under a broad class of risk objectives, characterized by convex scoring functions. This class covers many common risk measures, such as variance, Expected Shortfall, entropic Value-at-Risk,…

Mathematical Finance · Quantitative Finance 2025-05-16 Shanyu Han , Yang Liu , Xiang Yu

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

Systems and Control · Electrical Eng. & Systems 2020-09-29 Milad Kazemi , Sadegh Soudjani

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension…

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…

Machine Learning · Computer Science 2025-10-22 Youssef Mroueh

Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.…

Machine Learning · Computer Science 2020-10-13 Michael Zhang