English
Related papers

Related papers: NetHack is Hard to Hack

200 papers

There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning…

Artificial Intelligence · Computer Science 2018-10-18 Vlad Firoiu , Tina Ju , Josh Tenenbaum

We introduce an online active exploration algorithm for data-efficiently learning an abstract symbolic model of an environment. Our algorithm is divided into two parts: the first part quickly generates an intermediate Bayesian symbolic…

Artificial Intelligence · Computer Science 2017-11-02 Garrett Andersen , George Konidaris

AI systems are increasingly used to assist humans in sequential decision-making tasks, yet determining when and how an AI assistant should intervene remains a fundamental challenge. A potential baseline is to recommend the optimal action…

Artificial Intelligence · Computer Science 2026-04-17 Saumik Narayanan , Raja Panjwani , Siddhartha Sen , Chien-Ju Ho

Action quality assessment (AQA) applies computer vision to quantitatively assess the performance or execution of a human action. Current AQA approaches are end-to-end neural models, which lack transparency and tend to be biased because they…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Lauren Okamoto , Paritosh Parmar

Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning. Using these algorithms in multiagent environments poses problems such as nonstationarity and instability.…

Multiagent systems provide an ideal environment for the evaluation and analysis of real-world problems using reinforcement learning algorithms. Most traditional approaches to multiagent learning are affected by long training periods as well…

Artificial Intelligence · Computer Science 2021-05-25 Unnikrishnan Rajendran Menon , Anirudh Rajiv Menon

Real-time heuristic search is a popular model of acting and learning in intelligent autonomous agents. Learning real-time search agents improve their performance over time by acquiring and refining a value function guiding the application…

Artificial Intelligence · Computer Science 2007-05-23 Vadim Bulitko

Learning effective policies for sparse objectives is a key challenge in Deep Reinforcement Learning (RL). A common approach is to design task-related dense rewards to improve task learnability. While such rewards are easily interpreted,…

Machine Learning · Computer Science 2020-10-12 Hassam Sheikh , Shauharda Khadka , Santiago Miret , Somdeb Majumdar

Recent advances in Deep Reinforcement Learning (DRL) have largely focused on improving the performance of agents with the aim of replacing humans in known and well-defined environments. The use of these techniques as a game design tool for…

Machine Learning · Computer Science 2020-12-08 Alessandro Sestini , Alexander Kuhnle , Andrew D. Bagdanov

Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models rely on a large number of learned parameters, tightly couple feature extraction with…

Artificial Intelligence · Computer Science 2026-05-12 Adam Gould , Francesca Toni

We analyze the hidden activations of neural network policies of deep reinforcement learning (RL) agents and show, empirically, that it's possible to know a priori if a state representation will lend itself to fast learning. RL agents in…

Machine Learning · Computer Science 2021-03-12 Trevor A. McInroe , Michael Spurrier , Jennifer Sieber , Stephen Conneely

This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and…

Robotics · Computer Science 2026-03-03 Hakan Aktas , Yigit Yildirim , Ahmet Firat Gamsiz , Deniz Bilge Akkoc , Erhan Oztop , Emre Ugur

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark. In this work, we propose a new light-weight…

Machine Learning · Computer Science 2020-07-14 Siwei Chen , Xiao Ma , David Hsu

Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed…

Artificial Intelligence · Computer Science 2019-12-02 Vishal Jain , William Fedus , Hugo Larochelle , Doina Precup , Marc G. Bellemare

In Markov games, playing against non-stationary opponents with learning ability is still challenging for reinforcement learning (RL) agents, because the opponents can evolve their policies concurrently. This increases the complexity of the…

Artificial Intelligence · Computer Science 2020-05-27 Hao Chen , Chang Wang , Jian Huang , Jianxing Gong

How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional compute? The standard RL framework does not provide a…

Machine Learning · Computer Science 2026-02-18 Raj Ghugare , Michał Bortkiewicz , Alicja Ziarko , Benjamin Eysenbach

Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically. Neuro-symbolic approaches overcome this issue by mapping raw data to latent symbolic concepts using a neural network.…

Machine Learning · Computer Science 2023-10-10 Theo Charalambous , Yaniv Aspis , Alessandra Russo

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges…

Artificial Intelligence · Computer Science 2026-05-14 Hao Wang , Hanchen Li , Qiuyang Mang , Alvin Cheung , Koushik Sen , Dawn Song

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended…

Machine Learning · Computer Science 2026-05-21 Amit Roth , Ankur Samanta , Matan Halevy , Yoav Levine , Yonathan Efroni

We develop a method that integrates the tree of thoughts and multi-agent framework to enhance the capability of pre-trained language models in solving complex, unfamiliar games. The method decomposes game-solving into four incremental tasks…

Artificial Intelligence · Computer Science 2024-10-22 Yunhao Yang , Leonard Berthellemy , Ufuk Topcu