English
Related papers

Related papers: Is Policy Learning Overrated?: Width-Based Plannin…

200 papers

Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input. One successful approach, RolloutIW, represents states with the B-PROST boolean feature set. An augmented version…

Artificial Intelligence · Computer Science 2021-03-16 Andrea Dittadi , Frederik K. Drachmann , Thomas Bolander

Width-based planning has demonstrated great success in recent years due to its ability to scale independently of the size of the state space. For example, Bandres et al. (2018) introduced a rollout version of the Iterated Width algorithm…

Artificial Intelligence · Computer Science 2021-10-06 Miquel Junyent , Anders Jonsson , Vicenç Gómez

We propose new width-based planning and learning algorithms inspired from a careful analysis of the design decisions made by previous width-based planners. The algorithms are applied over the Atari-2600 games and our best performing…

Artificial Intelligence · Computer Science 2021-10-29 Stefan O'Toole , Nir Lipovetzky , Miquel Ramirez , Adrian Pearce

Optimal action selection in decision problems characterized by sparse, delayed rewards is still an open challenge. For these problems, current deep reinforcement learning methods require enormous amounts of data to learn controllers that…

Artificial Intelligence · Computer Science 2018-06-18 Miquel Junyent , Anders Jonsson , Vicenç Gómez

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning,…

Machine Learning · Computer Science 2013-12-20 Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Alex Graves , Ioannis Antonoglou , Daan Wierstra , Martin Riedmiller

Recently, width-based planning methods have been shown to yield state-of-the-art results in the Atari 2600 video games. For this, the states were associated with the (RAM) memory states of the simulator. In this work, we consider the same…

Artificial Intelligence · Computer Science 2018-01-11 Wilmer Bandres , Blai Bonet , Hector Geffner

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more,…

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…

Artificial Intelligence · Computer Science 2017-08-18 Felix Leibfried , Nate Kushman , Katja Hofmann

Although deep reinforcement learning methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex, and training times are often long. This study investigates how Evolution…

Machine Learning · Computer Science 2024-07-25 Annie Wong , Jacob de Nobel , Thomas Bäck , Aske Plaat , Anna V. Kononova

Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari games. These methods scale independently of the size of the…

Artificial Intelligence · Computer Science 2022-04-29 Miquel Junyent , Vicenç Gómez , Anders Jonsson

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high…

Machine Learning · Computer Science 2018-11-20 Feiyang Pan , Qingpeng Cai , An-Xiang Zeng , Chun-Xiang Pan , Qing Da , Hualin He , Qing He , Pingzhong Tang

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss…

Machine Learning · Computer Science 2019-10-09 Xue Bin Peng , Aviral Kumar , Grace Zhang , Sergey Levine

Some of the most powerful reinforcement learning frameworks use planning for action selection. Interestingly, their planning horizon is either fixed or determined arbitrarily by the state visitation history. Here, we expand beyond the naive…

Machine Learning · Computer Science 2023-01-19 Aviv Rosenberg , Assaf Hallak , Shie Mannor , Gal Chechik , Gal Dalal

Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While…

Machine Learning · Computer Science 2022-02-15 Danijar Hafner , Timothy Lillicrap , Mohammad Norouzi , Jimmy Ba

The Arcade Learning Environment (ALE) is proposed as an evaluation platform for empirically assessing the generality of agents across dozens of Atari 2600 games. ALE offers various challenging problems and has drawn significant attention…

Artificial Intelligence · Computer Science 2023-02-28 Jiajun Fan

Cognitive science and psychology suggest that object-centric representations of complex scenes are a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep reinforcement learning…

Machine Learning · Computer Science 2024-02-28 Quentin Delfosse , Jannis Blüml , Bjarne Gregori , Sebastian Sztwiertnia , Kristian Kersting

Real-time video applications require dynamic bitrate adjustments based on network capacity, necessitating accurate bandwidth estimation (BWE). We introduce Ivy, a novel BWE method that leverages offline meta-learning to combat data drift…

Networking and Internet Architecture · Computer Science 2026-03-25 Aashish Gottipati , Sami Khairy , Yasaman Hosseinkashi , Gabriel Mittag , Vishak Gopal , Francis Y. Yan , Ross Cutler

In reinforcement learning, the advantage function is critical for policy improvement, but is often extracted from a learned Q-function. A natural question is: Why not learn the advantage function directly? In this work, we introduce…

Machine Learning · Computer Science 2024-09-04 Yunhao Tang , Rémi Munos , Mark Rowland , Michal Valko

Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially…

Machine Learning · Computer Science 2020-04-01 Kacper Kielak

Much human and computational effort has aimed to improve how deep reinforcement learning algorithms perform on benchmarks such as the Atari Learning Environment. Comparatively less effort has focused on understanding what has been learned…

Neural and Evolutionary Computing · Computer Science 2019-05-31 Felipe Petroski Such , Vashisht Madhavan , Rosanne Liu , Rui Wang , Pablo Samuel Castro , Yulun Li , Jiale Zhi , Ludwig Schubert , Marc G. Bellemare , Jeff Clune , Joel Lehman
‹ Prev 1 2 3 10 Next ›