English
Related papers

Related papers: Introspective Experience Replay: Look Back When Su…

200 papers

Recent advancements in LLM post-training, particularly through reinforcement learning and preference optimization, are key to boosting their reasoning capabilities. However, these methods often suffer from low sample efficiency and a…

Machine Learning · Computer Science 2026-05-08 Zichuan Liu , Jinyu Wang , Lei Song , Jiang Bian

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational…

Machine Learning · Computer Science 2024-01-31 Gokul Swamy , Sanjiban Choudhury , J. Andrew Bagnell , Zhiwei Steven Wu

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

Machine Learning · Computer Science 2021-06-01 Sobirdzhon Bobiev , Adil Khan , Syed Muhammad Ahsan Raza Kazmi

Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm for sparse reward functions. The algorithm treats every failure as a success for an alternative (virtual) goal that has been achieved in the episode. Virtual…

Machine Learning · Computer Science 2021-03-09 Binyamin Manela , Armin Biess

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Machine Learning · Computer Science 2019-10-31 Rahaf Aljundi , Lucas Caccia , Eugene Belilovsky , Massimo Caccia , Min Lin , Laurent Charlin , Tinne Tuytelaars

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To address this, some methods propose replaying data from previous…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Chenyang Wang , Junjun Jiang , Xingyu Hu , Xianming Liu , Xiangyang Ji

Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner. However, the non-stationary nature of streaming training data…

Machine Learning · Computer Science 2024-05-14 Xingyu Li , Bo Tang , Haifeng Li

Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes, while maintaining the knowledge already learned for old classes. Saving a subset of training samples of previously seen…

Computer Vision and Pattern Recognition · Computer Science 2021-04-22 Jian Jiang , Edoardo Cetin , Oya Celiktutan

The embedding-based retrieval (EBR) approach is widely used in mainstream search engine retrieval systems and is crucial in recent retrieval-augmented methods for eliminating LLM illusions. However, existing EBR models often face the…

Computation and Language · Computer Science 2024-04-10 Yanan Zhang , Xiaoling Bai , Tianhua Zhou

In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, recentness and…

Machine Learning · Computer Science 2021-11-10 Xu-Hui Liu , Zhenghai Xue , Jing-Cheng Pang , Shengyi Jiang , Feng Xu , Yang Yu

Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a…

Machine Learning · Computer Science 2021-06-15 Minqi Jiang , Edward Grefenstette , Tim Rocktäschel

Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $\lambda$-return difficult in this context. In particular, off-policy methods that…

Machine Learning · Computer Science 2020-01-15 Brett Daley , Christopher Amato

A central component of training in Reinforcement Learning (RL) is Experience: the data used for training. The mechanisms used to generate and consume this data have an important effect on the performance of RL algorithms. In this paper, we…

Machine Learning · Computer Science 2021-02-10 Albin Cassirer , Gabriel Barth-Maron , Eugene Brevdo , Sabela Ramos , Toby Boyd , Thibault Sottiaux , Manuel Kroiss

In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate…

Robotics · Computer Science 2024-09-25 Xinda Qi , Dong Chen , Zhaojian Li , Xiaobo Tan

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

Machine Learning · Computer Science 2022-11-30 Jingda Wu , Zhiyu Huang , Wenhui Huang , Chen Lv

Hindsight Experience Replay (HER) is one of the efficient algorithm to solve Reinforcement Learning tasks related to sparse rewarded environments.But due to its reduced sample efficiency and slower convergence HER fails to perform…

Machine Learning · Computer Science 2020-10-14 Dhuruva Priyan G M , Abhik Singla , Shalabh Bhatnagar

In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses…

Machine Learning · Computer Science 2024-06-18 Utsav Singh , Wesley A. Suttle , Brian M. Sadler , Vinay P. Namboodiri , Amrit Singh Bedi

Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…

Machine Learning · Computer Science 2023-11-21 Tiantian Zhang , Kevin Zehua Shen , Zichuan Lin , Bo Yuan , Xueqian Wang , Xiu Li , Deheng Ye

Policy gradient reinforcement learning (RL) algorithms have achieved impressive performance in challenging learning tasks such as continuous control, but suffer from high sample complexity. Experience replay is a commonly used approach to…

Machine Learning · Statistics 2020-02-19 Saad Mohamad , Giovanni Montana

A key theme in the past decade has been that when large neural networks and large datasets combine they can produce remarkable results. In deep reinforcement learning (RL), this paradigm is commonly made possible through experience replay,…

Machine Learning · Computer Science 2023-10-30 Cong Lu , Philip J. Ball , Yee Whye Teh , Jack Parker-Holder