English
Related papers

Related papers: Conservative Exploration using Interleaving

200 papers

The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests…

Machine Learning · Computer Science 2024-07-03 Jibang Wu , Siyu Chen , Mengdi Wang , Huazheng Wang , Haifeng Xu

We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity,…

Machine Learning · Computer Science 2024-08-19 Victor Kolev , Rafael Rafailov , Kyle Hatch , Jiajun Wu , Chelsea Finn

As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However,…

Robotics · Computer Science 2025-07-29 Hanne Say , Suzan Ece Ada , Emre Ugur , Minoru Asada , Erhan Oztop

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…

Machine Learning · Computer Science 2024-02-26 Martin Benfeghoul , Umais Zahid , Qinghai Guo , Zafeirios Fountas

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before…

Machine Learning · Computer Science 2023-07-19 Saeed Ghoorchian , Evgenii Kortukov , Setareh Maghsudi

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call…

Machine Learning · Computer Science 2020-01-17 Haitao Xu , Brendan McCane , Lech Szymanski , Craig Atkinson

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Machine Learning · Computer Science 2022-03-01 Nikunj Saunshi , Jordan Ash , Surbhi Goel , Dipendra Misra , Cyril Zhang , Sanjeev Arora , Sham Kakade , Akshay Krishnamurthy

We propose $\textit{iterative inversion}$ -- an algorithm for learning an inverse function without input-output pairs, but only with samples from the desired output distribution and access to the forward function. The key challenge is a…

Machine Learning · Computer Science 2023-05-31 Gal Leibovich , Guy Jacob , Or Avner , Gal Novik , Aviv Tamar

Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are…

Artificial Intelligence · Computer Science 2026-02-05 Feiyu Gavin Zhu , Jean Oh , Reid Simmons

We study the problem of pure exploration in matching markets under uncertain preferences, where the goal is to identify a stable matching with confidence parameter $\delta$ and minimal sample complexity. Agents learn preferences via…

Computer Science and Game Theory · Computer Science 2025-09-19 Tejas Pagare , Agniv Bandyopadhyay , Sandeep Juneja

A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy…

Machine Learning · Computer Science 2023-02-27 Wanqiao Xu , Jason Yecheng Ma , Kan Xu , Hamsa Bastani , Osbert Bastani

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the…

Computer Science and Game Theory · Computer Science 2019-11-21 Tobias Baumann , Thore Graepel , John Shawe-Taylor

We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic…

Machine Learning · Computer Science 2022-06-14 Thomas Kleine Buening , Anne-Marie George , Christos Dimitrakakis

Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful…

Machine Learning · Computer Science 2019-12-03 Daniel Moyer , Shuyang Gao , Rob Brekelmans , Greg Ver Steeg , Aram Galstyan

We study the problem of guaranteeing low regret in repeated games against an opponent with unknown membership in one of several classes. We add the constraint that our algorithm is non-exploitable, in that the opponent lacks an incentive to…

Computer Science and Game Theory · Computer Science 2022-07-05 Anthony DiGiovanni , Ambuj Tewari

We study the repeated principal-agent bandit game, where the principal indirectly interacts with the unknown environment by proposing incentives for the agent to play arms. Most existing work assumes the agent has full knowledge of the…

Machine Learning · Computer Science 2025-06-03 Junyan Liu , Lillian J. Ratliff

Recommendation systems often face exploration-exploitation tradeoffs: the system can only learn about the desirability of new options by recommending them to some user. Such systems can thus be modeled as multi-armed bandit settings;…

Computer Science and Game Theory · Computer Science 2020-07-02 Gal Bahar , Omer Ben-Porat , Kevin Leyton-Brown , Moshe Tennenholtz

Imitation learning suffers from causal confusion. This phenomenon occurs when learned policies attend to features that do not causally influence the expert actions but are instead spuriously correlated. Causally confused agents produce low…

Machine Learning · Computer Science 2023-08-14 Samuel Pfrommer , Yatong Bai , Hyunin Lee , Somayeh Sojoudi

In real-world reinforcement learning (RL) systems, various forms of {\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due to latency or lossy…

Machine Learning · Computer Science 2023-10-30 Minshuo Chen , Jie Meng , Yu Bai , Yinyu Ye , H. Vincent Poor , Mengdi Wang

When learning to play an imperfect information game, it is often easier to first start with the basic mechanics of the game rules. For example, one can play several example rounds with private cards revealed to all players to better…

Computer Science and Game Theory · Computer Science 2025-05-27 Benjamin Heymann , Marc Lanctot