paper-with-me

Papers

Retrieval-Augmented Reinforcement Learning

2022-02-17 · Anirudh Goyal, Abram L. Friesen, Andrea Banino, Theophane Weber, Nan Rosemary Ke, Adria Puigdomenech Badia, Arthur Guez, Mehdi Mirza, Peter C. Humphreys, Ksenia Konyushkova, Laurent SIfre, Michal Valko, Simon Osindero, Timothy Lillicrap, Nicolas Heess, Charles Blundell

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive, (2) it can take many updates to integrate experiences into the parametric model, (3) experiences that are not fully integrated do not appropriately influence the agent's behavior, and (4) behavior is limited by the capacity of the model. In this paper we explore an alternative paradigm in which we train a network to map a dataset of past experiences to optimal behavior. Specifically, we augment an RL agent with a retrieval process (parameterized as a neural network) that has direct access to a dataset of experiences. This dataset can come from the agent's past experiences, expert demonstrations, or any other relevant source. The retrieval process is trained to retrieve information from the dataset that may be useful in the current context, to help the agent achieve its goal faster and more efficiently. he proposed method facilitates learning agents that at test-time can condition their behavior on the entire dataset and not only the current state, or current trajectory. We integrate our method into two different RL agents: an offline DQN agent and an online R2D2 agent. In offline multi-task problems, we show that the retrieval-augmented DQN agent avoids task interference and learns faster than the baseline DQN agent. On Atari, we show that retrieval-augmented R2D2 learns significantly faster than the baseline R2D2 agent and achieves higher scores. We run extensive ablations to measure the contributions of the components of our proposed method.

📄 PDF Abstract BibTeX arXiv:2202.08417

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Retrieval

Methods 이 논문이 사용한 방법론

R2D2 Building on the recent successes of distributed training of RL agents, R2D2 is an RL approach that trains a RNN-based RL agents from distributed prioritized experience replay.…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

MMRAG-RFT: Two-stage Reinforcement Fine-tuning for Explainable Multi-modal Retrieval-augmented Generation

2025-12-19 · Shengwei Zhao, Jingwen Yao, Sitong Wei, Linhai Xu 외 arxiv

Multi-modal Retrieval-Augmented Generation (MMRAG) enables highly credible generation by integrating external multi-modal knowledge, thus demonstrating impressive performance in complex multi-modal scenarios. However, ex…

Reinforcement LearningResponse GenerationAnswer Generation

Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning

2026-06-11 · Zilin Xiao, Qi Ma, Chun-cheng Jason Chen, Xintao Chen 외 arxiv

Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex re…

Mathematical ReasoningSemantic Similarity

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

2024-10-22 · Zongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou 외

Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect to retrieval augmentation. Despite bein…

RetrievalRetrieval-augmented Generation

Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation

2026-01-21 · Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang 외 arxiv

Multilingual retrieval-augmented generation (MRAG) requires models to effectively acquire and integrate beneficial external knowledge from multilingual collections. However, most existing studies employ a unitive process…

Reinforcement Learning

Optimizing Retrieval for RAG via Reinforcement Learning

2025-10-28 · Jiawei Zhou, Lei Chen arxiv

As retrieval-augmented generation (RAG) becomes more widespread, the role of retrieval is shifting from retrieving information for human browsing to retrieving context for AI reasoning. This shift creates more complex se…

Reinforcement Learning