English
Related papers

Related papers: SuS: Strategy-aware Surprise for Intrinsic Explora…

200 papers

The performance of Recommender Systems (RS) varies significantly across users, yet the underlying reasons for this variance remain poorly understood. This paper introduces a unified framework to analyze and explain this performance gap by…

Information Retrieval · Computer Science 2026-03-04 Michaël Soumm , Alexandre Fournier-Montgieux , Adrian Popescu , Bertrand Delezoide

Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rewards. In this work,…

Machine Learning · Computer Science 2022-05-20 Jianren Wang , Ziwen Zhuang , Hang Zhao

The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement…

Machine Learning · Computer Science 2022-02-24 Pietro Mazzaglia , Ozan Catal , Tim Verbelen , Bart Dhoedt

Reinforcement learning involves agents interacting with an environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the quality of actions that they take, thereby…

Multiagent Systems · Computer Science 2022-02-22 Baicen Xiao , Bhaskar Ramasubramanian , Radha Poovendran

We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and…

Machine Learning · Computer Science 2012-05-14 John Asmuth , Lihong Li , Michael L. Littman , Ali Nouri , David Wingate

Surprise-based learning allows agents to rapidly adapt to non-stationary stochastic environments characterized by sudden changes. We show that exact Bayesian inference in a hierarchical model gives rise to a surprise-modulated trade-off…

Machine Learning · Statistics 2020-09-25 Vasiliki Liakoni , Alireza Modirshanechi , Wulfram Gerstner , Johanni Brea

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy. This contributes to the problem of high sample complexity,…

Machine Learning · Computer Science 2019-11-21 Tom Blau , Lionel Ott , Fabio Ramos

An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in tabular settings. However, in non-tabular settings that…

We introduce a new unsupervised pretraining objective for reinforcement learning. During the unsupervised reward-free pretraining phase, the agent maximizes mutual information between tasks and states induced by the policy. Our key…

Machine Learning · Computer Science 2021-09-01 Hao Liu , Pieter Abbeel

Decisions made by machine learning systems have increasing influence on the world, yet it is common for machine learning algorithms to assume that no such influence exists. An example is the use of the i.i.d. assumption in content…

Machine Learning · Computer Science 2020-09-22 David Krueger , Tegan Maharaj , Jan Leike

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating…

Machine Learning · Computer Science 2022-05-26 Xinran Liang , Katherine Shu , Kimin Lee , Pieter Abbeel

Effective exploration is critical for reinforcement learning agents in environments with sparse rewards or high-dimensional state-action spaces. Recent works based on state-visitation counts, curiosity and entropy-maximization generate…

Machine Learning · Computer Science 2022-09-13 Bang You , Jingming Xie , Youping Chen , Jan Peters , Oleg Arenz

Autonomous exploration in complex multi-agent reinforcement learning (MARL) with sparse rewards critically depends on providing agents with effective intrinsic motivation. While artificial curiosity offers a powerful self-supervised signal,…

Machine Learning · Computer Science 2026-02-24 Yiyuan Pan , Zhe Liu , Hesheng Wang

We introduce Self-supervised Online Reward Shaping (SORS), which aims to improve the sample efficiency of any RL algorithm in sparse-reward environments by automatically densifying rewards. The proposed framework alternates between…

Machine Learning · Computer Science 2021-07-27 Farzan Memarian , Wonjoon Goo , Rudolf Lioutikov , Scott Niekum , Ufuk Topcu

We introduce Sophisticated Learning (SL), a planning-to-learn algorithm that embeds active parameter learning inside the Sophisticated Inference (SI) tree-search framework of Active Inference. Unlike SI -- which optimizes beliefs about…

Artificial Intelligence · Computer Science 2025-08-18 Rowan Hodson , Bruce Bassett , Charel van Hoof , Benjamin Rosman , Mark Solms , Jonathan P. Shock , Ryan Smith

Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for exploring such environments is to introduce some "intrinsic"…

Machine Learning · Computer Science 2020-07-16 Neale Ratzlaff , Qinxun Bai , Li Fuxin , Wei Xu

Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward…

Machine Learning · Computer Science 2021-03-16 Rui Zhao , Yang Gao , Pieter Abbeel , Volker Tresp , Wei Xu

Inspired by the notion of surprise for unconventional discovery we introduce a general search algorithm we name surprise search as a new method of evolutionary divergent search. Surprise search is grounded in the divergent search paradigm…

Neural and Evolutionary Computing · Computer Science 2017-06-09 Daniele Gravina , Antonios Liapis , Georgios N. Yannakakis

In vision-based reinforcement learning (RL) tasks, it is prevalent to assign auxiliary tasks with a surrogate self-supervised loss so as to obtain more semantic representations and improve sample efficiency. However, abundant information in…

Machine Learning · Computer Science 2022-05-16 Yue Zhao , Chenzhuang Du , Hang Zhao , Tiejun Li

Standard selective prediction methods typically estimate uncertainty from the output of a single predictive branch. While effective for general uncertainty estimation, these approaches often struggle under partial observability, where local…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Kartik Jhawar , Yuhao Geng , Atul N. Parikh , Lipo Wang