no code implementations • 5 Mar 2024 • Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Yi Xia, Pratch Suntichaikul, Ruck Thawonmas, Julian Togelius, Jochen Renz
We thoroughly evaluate the effectiveness of the new metric and the improved classifier.
no code implementations • 18 Dec 2023 • Cheng Xue, Ekaterina Nikonova, Peng Zhang, Jochen Renz
This is an important characteristic of intelligent agents, as it allows them to continue to function effectively in novel or unexpected situations, but still stands as a critical challenge for deep reinforcement learning (DRL).
no code implementations • 24 Nov 2023 • Ekaterina Nikonova, Cheng Xue, Jochen Renz
In this work, we propose a general framework that is applicable to deep reinforcement learning agents.
no code implementations • 5 Aug 2023 • Chathura Gamage, Vimukthini Pinto, Matthew Stephenson, Jochen Renz
We believe that the tasks generated using our proposed methodology can facilitate a nuanced evaluation of physical reasoning agents, thus paving the way for the development of agents for more sophisticated real-world applications.
1 code implementation • 28 Mar 2023 • Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Ruck Thawonmas, Julian Togelius, Jochen Renz
An experiment is conducted to determine the effectiveness of several modified versions of this sample prompt on level stability and similarity by testing them on several characters.
1 code implementation • 3 Mar 2023 • Chathura Gamage, Vimukthini Pinto, Cheng Xue, Peng Zhang, Ekaterina Nikonova, Matthew Stephenson, Jochen Renz
But is it enough to only have physical reasoning capabilities to operate in a real physical environment?
no code implementations • 28 Dec 2022 • Ekaterina Nikonova, Cheng Xue, Jochen Renz
During training, reinforcement learning systems interact with the world without considering the safety of their actions.
no code implementations • 28 Jul 2022 • Ekaterina Nikonova, Cheng Xue, Vimukthini Pinto, Chathura Gamage, Peng Zhang, Jochen Renz
In this paper, we propose to define the novelty reaction difficulty as a relative difficulty of performing the known task after the introduction of the novelty.
1 code implementation • 31 Aug 2021 • Cheng Xue, Vimukthini Pinto, Chathura Gamage, Ekaterina Nikonova, Peng Zhang, Jochen Renz
Inspired by how human IQ is calculated, we define the physical reasoning quotient (Phy-Q score) that reflects the physical reasoning intelligence of an agent using the physical scenarios we considered.
1 code implementation • 17 Jun 2021 • Cheng Xue, Vimukthini Pinto, Chathura Gamage, Peng Zhang, Jochen Renz
In this paper, we propose a new benchmark for physical reasoning that allows us to test individual physical reasoning capabilities.
no code implementations • 16 Jun 2021 • Vimukthini Pinto, Cheng Xue, Chathura Nagoda Gamage, Matthew Stephenson, Jochen Renz
Therefore, to accurately evaluate the novelty detection capability of AI systems, it is necessary to investigate how difficult it may be to detect different types of novelty.
no code implementations • 3 Jun 2021 • Chathura Gamage, Matthew Stephenson, Vimukthini Pinto, Jochen Renz
The Angry Birds AI competition has been held over many years to encourage the development of AI agents that can play Angry Birds game levels better than human players.
no code implementations • 25 Sep 2019 • Ekaterina Nikonova, Jochen Renz
We show that by using physical laws together with deep learning we achieve a better human-interpretability of learned physical properties, transfer of knowledge to a game with similar physics and very accurate predictions for previously unseen data.
1 code implementation • 30 May 2019 • Tommy Liu, Jochen Renz, Peng Zhang, Matthew Stephenson
Over the past few years the Angry Birds AI competition has been held in an attempt to develop intelligent agents that can successfully and efficiently solve levels for the video game Angry Birds.
no code implementations • 10 May 2019 • Peng Zhang, Xiaoyu Ge, Jochen Renz
Understanding physical relations between objects, especially their support relations, is crucial for robotic manipulation.
no code implementations • 7 Feb 2019 • Matthew Stephenson, Jochen Renz
This paper presents an adaptive level generation algorithm for the physics-based puzzle game Angry Birds.
1 code implementation • 9 Sep 2018 • Matthew Stephenson, Damien Anderson, Ahmed Khalifa, John Levine, Jochen Renz, Julian Togelius, Christoph Salge
This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms.
no code implementations • 28 Jul 2018 • Xiaoyu Ge, Jochen Renz, Hua Hua
However, there has been no suitable qualitative theory proposed for object motion in three-dimensional space.
no code implementations • 14 Mar 2018 • Matthew Stephenson, Jochen Renz, Xiaoyu Ge, Peng Zhang
This paper presents an overview of the sixth AIBIRDS competition, held at the 26th International Joint Conference on Artificial Intelligence.
no code implementations • 31 Jan 2018 • Damien Anderson, Matthew Stephenson, Julian Togelius, Christian Salge, John Levine, Jochen Renz
Deceptive games are games where the reward structure or other aspects of the game are designed to lead the agent away from a globally optimal policy.