English
Related papers

Related papers: Value function estimation using conditional diffus…

200 papers

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL methods improve…

Model-based reinforcement learning (RL) methods are appealing in the offline setting because they allow an agent to reason about the consequences of actions without interacting with the environment. Prior methods learn a 1-step dynamics…

Machine Learning · Computer Science 2022-11-07 Bogdan Mazoure , Benjamin Eysenbach , Ofir Nachum , Jonathan Tompson

Training deep reinforcement learning agents on environments with multiple levels / scenes from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to the real world.…

Machine Learning · Computer Science 2021-02-16 Jaskirat Singh , Liang Zheng

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem…

Machine Learning · Computer Science 2026-04-21 Angelo Moroncelli , Matteo Rufolo , Gunes Cagin Aydin , Asad Ali Shahid , Loris Roveda

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

Robotics · Computer Science 2025-09-18 Xiatao Sun , Francis Fan , Yinxing Chen , Daniel Rakita

The aim of this paper is to study the reward based policy exploration problem in a supervised learning approach and enable robots to form complex movement trajectories in challenging reward settings and search spaces. For this, the…

Robotics · Computer Science 2020-11-10 M. Tuluhan Akbulut , Utku Bozdogan , Ahmet Tekden , Emre Ugur

Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale…

Diffusion-based models have achieved notable empirical successes in reinforcement learning (RL) due to their expressiveness in modeling complex distributions. Despite existing methods being promising, the key challenge of extending existing…

Machine Learning · Computer Science 2024-11-04 Dmitry Shribak , Chen-Xiao Gao , Yitong Li , Chenjun Xiao , Bo Dai

We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations…

Machine Learning · Computer Science 2025-12-18 Hanqing Jin , Renyuan Xu , Yanzhao Yang

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward…

Machine Learning · Computer Science 2019-05-28 Hongyao Tang , Jianye Hao , Guangyong Chen , Pengfei Chen , Zhaopeng Meng , Yaodong Yang , Li Wang

This work shows that value-aware model learning, known for its numerous theoretical benefits, is also practically viable for solving challenging continuous control tasks in prevalent model-based reinforcement learning algorithms. First, we…

Machine Learning · Computer Science 2022-01-31 Nirbhay Modhe , Harish Kamath , Dhruv Batra , Ashwin Kalyan

We propose a distributed deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is based on the deep Q-network, a convolutional neural network trained…

Machine Learning · Computer Science 2015-10-16 Hao Yi Ong , Kevin Chavez , Augustus Hong

Fine-tuning foundation models via reinforcement learning (RL) has proven promising for aligning to downstream objectives. In the case of diffusion models (DMs), though RL training improves alignment from early timesteps, critical issues…

Machine Learning · Statistics 2024-10-14 Roberto Barceló , Cristóbal Alcázar , Felipe Tobar

Learning-based methods have been used to pro-gram robotic tasks in recent years. However, extensive training is usually required not only for the initial task learning but also for generalizing the learned model to the same task but in…

Robotics · Computer Science 2019-12-12 Tianying Wang , Hao Zhang , Wei Qi Toh , Hongyuan Zhu , Cheston Tan , Yan Wu , Yong Liu , Wei Jing

Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train policies over extended time horizons by structuring high-level…

Robotics · Computer Science 2024-12-16 Mattijs Baert , Sam Leroux , Pieter Simoens

In reinforcement learning, the value function is typically trained to solve the Bellman equation, which connects the current value to future values. This temporal dependency hints that the value function may contain implicit information…

Machine Learning · Computer Science 2025-01-17 Jacob Adamczyk

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a…

Machine Learning · Computer Science 2022-09-14 Haoxin Lin , Yihao Sun , Jiaji Zhang , Yang Yu

For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents. While model-based agents are conceptually appealing,…

Machine Learning · Computer Science 2021-05-28 Brandon Amos , Samuel Stanton , Denis Yarats , Andrew Gordon Wilson

Diffusion policies trained via offline behavioral cloning have recently gained traction in robotic motion generation. While effective, these policies typically require a large number of trainable parameters. This model size affords powerful…

Robotics · Computer Science 2025-04-29 Xiatao Sun , Shuo Yang , Yinxing Chen , Francis Fan , Yiyan Liang , Daniel Rakita