paper-with-me

Papers

RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning

2022-04-26 · Marc Rigter, Bruno Lacerda, Nick Hawes

Offline reinforcement learning (RL) aims to find performant policies from logged data without further environment interaction. Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy optimisation within that model, have emerged as a promising approach to this problem. In this work, we present Robust Adversarial Model-Based Offline RL (RAMBO), a novel approach to model-based offline RL. We formulate the problem as a two-player zero sum game against an adversarial environment model. The model is trained to minimise the value function while still accurately predicting the transitions in the dataset, forcing the policy to act conservatively in areas not covered by the dataset. To approximately solve the two-player game, we alternate between optimising the policy and adversarially optimising the model. The problem formulation that we address is theoretically grounded, resulting in a probably approximately correct (PAC) performance guarantee and a pessimistic value function which lower bounds the value function in the true environment. We evaluate our approach on widely studied offline RL benchmarks, and demonstrate that it outperforms existing state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2204.12581

Code (2)

marc-rigter/rambo 공식 구현 pytorch
yihaosun1124/OfflineRL-Kit pytorch

Tasks

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting

2026-03-09 · Zhongjian Qiao, Jiafei Lyu, Boxiang Lyu, Yao Shu 외 arxiv

Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, \textit{model exploitation} could occur due to inevitable model errors, degra…

Reinforcement LearningOffline RL

RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit

2021-12-10 · Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe

Machine learning models are critically susceptible to evasion attacks from adversarial examples. Generally, adversarial examples, modified inputs deceptively similar to the original input, are constructed under whitebox …

RAMBO: Enhancing RAG-based Repository-Level Method Body Completion

2024-09-23 · Tuan-Dung Bui, Duc-Thieu Luu-Van, Thanh-Phat Nguyen, Thu-Trang Nguyen 외

Code completion is essential in software development, helping developers by predicting code snippets based on context. Among completion tasks, Method Body Completion (MBC) is particularly challenging as it involves gener…

Code CompletionCode GenerationRAG

ParamBoost: Gradient Boosted Piecewise Cubic Polynomials

2026-04-20 · Nicolas Salvadé, Tim Hillel arxiv

Generalized Additive Models (GAMs) can be used to create non-linear glass-box (i.e. explicitly interpretable) models, where the predictive function is fully observable over the complete input space. However, glass-box in…

Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation

2025-03-26 · Hongye Cao, Fan Feng, Jing Huo, Shangdong Yang 외

Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble mo…

D4RLData AugmentationOffline RLreinforcement-learning+2