English
Related papers

Related papers: Before we can find a model, we must forget about p…

200 papers

World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World models typically…

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

Machine Learning · Computer Science 2022-09-08 Nicholas A. Ketz , Praveen K. Pilly

We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market. At each step, the agents are presented with a dynamical context, where the contexts determine the utilities. The planner…

Machine Learning · Computer Science 2022-03-09 Yifei Min , Tianhao Wang , Ruitu Xu , Zhaoran Wang , Michael I. Jordan , Zhuoran Yang

Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement real trajectories, or sequences of sampled states over time, with simulated ones sampled from a…

Machine Learning · Computer Science 2018-05-28 Ryan Faulkner , Doina Precup

Reinforcement learning (RL) has gained increasing attraction in the academia and tech industry with launches to a variety of impactful applications and products. Although research is being actively conducted on many fronts (e.g., offline…

Machine Learning · Computer Science 2021-12-13 Ruiyang Xu , Zhengxing Chen

This work considers the sample and computational complexity of obtaining an $\epsilon$-optimal policy in a discounted Markov Decision Process (MDP), given only access to a generative model. In this work, we study the effectiveness of the…

Machine Learning · Computer Science 2020-04-07 Alekh Agarwal , Sham Kakade , Lin F. Yang

Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after…

Machine Learning · Computer Science 2022-06-22 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined…

Machine Learning · Computer Science 2018-03-02 Vladimir Feinberg , Alvin Wan , Ion Stoica , Michael I. Jordan , Joseph E. Gonzalez , Sergey Levine

The importance of hierarchically structured representations for tractable planning has long been acknowledged. However, the questions of how people discover such abstractions and how to define a set of optimal abstractions remain open. This…

Artificial Intelligence · Computer Science 2018-07-20 Sophia Sanborn , David D. Bourgin , Michael Chang , Thomas L. Griffiths

For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex…

Artificial Intelligence · Computer Science 2017-05-23 Min Xu

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

Sequential decision-making systems routinely operate with missing or incomplete data. Classical reinforcement learning theory, which is commonly used to solve sequential decision problems, assumes Markovian observability, which may not hold…

Machine Learning · Computer Science 2025-08-07 MaryLena Bleile , Minh-Nhat Phung , Minh-Binh Tran

Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches…

Machine Learning · Computer Science 2022-06-20 Tom Blau , Edwin V. Bonilla , Iadine Chades , Amir Dezfouli

Extrapolation in reinforcement learning is the ability to generalize at test time given states that could never have occurred at training time. Here we consider four factors that lead to improved extrapolation in a simple Gridworld…

Machine Learning · Computer Science 2020-04-16 Eugene Charniak

We propose and validate a novel car following model based on deep reinforcement learning. Our model is trained to maximize externally given reward functions for the free and car-following regimes rather than reproducing existing follower…

Machine Learning · Computer Science 2021-09-30 Fabian Hart , Ostap Okhrin , Martin Treiber

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error…

Artificial Intelligence · Computer Science 2017-08-22 Tom Everitt , Victoria Krakovna , Laurent Orseau , Marcus Hutter , Shane Legg

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Machine Learning · Computer Science 2018-07-11 Chi Jin , Zeyuan Allen-Zhu , Sebastien Bubeck , Michael I. Jordan

To overcome the curses of dimensionality and modeling of Dynamic Programming (DP) methods to solve Markov Decision Process (MDP) problems, Reinforcement Learning (RL) methods are adopted in practice. Contrary to traditional RL algorithms…

Machine Learning · Computer Science 2021-08-24 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

Lazy graph search algorithms are efficient at solving motion planning problems where edge evaluation is the computational bottleneck. These algorithms work by lazily computing the shortest potentially feasible path, evaluating edges along…

Robotics · Computer Science 2019-07-18 Mohak Bhardwaj , Sanjiban Choudhury , Byron Boots , Siddhartha Srinivasa

Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contrast, we consider agents that are not limited to passive…

Machine Learning · Computer Science 2025-10-20 Ziqing Lu , Babak Hassibi , Lifeng Lai , Weiyu Xu