98 citations · 246 across the 18 of their papers we have counts for
20 papers
At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier
Marco Dos Santos, Vivek Veeriah, Alex Havrilla +4
Recent breakthroughs in AI for mathematics---ranging from Olympiad medal performances to resolving long-standing open conjectures---have rapidly expanded what automated systems can…
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
Tom Zahavy, Shaobo Hou, Thomas Tumiel +16
While generative AI has achieved remarkable success in solving problems with verifiable solutions, generating physical art that satisfies both strict geometric constraints and subj…
Generating Creative Chess Puzzles
Xidong Feng, Vivek Veeriah, Marcus Chiam +10
While Generative AI rapidly advances in various domains, generating truly creative, aesthetic, and counter-intuitive outputs remains a challenge. This paper presents an approach to…
Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions
Vivek Veeriah, Federico Barbero, Marcus Chiam +10
The rapid advancement of Generative AI has raised significant questions regarding its ability to produce creative and novel outputs. Our recent work investigates this question with…
AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Tasks
Ryan Diaz, Adam Imdieke, Vivek Veeriah +1
Operating in unstructured environments like households requires robotic policies that are robust to out-of-distribution conditions. Although much work has been done in evaluating r…
Diversifying AI: Towards Creative Chess with AlphaZero
Tom Zahavy, Vivek Veeriah, Shaobo Hou +7
In recent years, Artificial Intelligence (AI) systems have surpassed human intelligence in a variety of computational tasks. However, AI systems, like humans, make mistakes, have b…
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah +3
In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's beha…
GrASP: Gradient-Based Affordance Selection for Planning
Vivek Veeriah, Zeyu Zheng, Richard Lewis +1
Planning with a learned model is arguably a key component of intelligence. There are several challenges in realizing such a component in large-scale reinforcement learning (RL) pro…
Discovery of Options via Meta-Learned Subgoals
Vivek Veeriah, Tom Zahavy, Matteo Hessel +6
Temporal abstractions in the form of options have been shown to help reinforcement learning (RL) agents learn faster. However, despite prior work on this topic, the problem of disc…
Learning State Representations from Random Deep Action-conditional Predictions
Zeyu Zheng, Vivek Veeriah, Risto Vuorio +2
Our main contribution in this work is an empirical finding that random General Value Functions (GVFs), i.e., deep action-conditional predictions -- random both in what feature of o…
Learning Retrospective Knowledge with Reverse Reinforcement Learning
Shangtong Zhang, Vivek Veeriah, Shimon Whiteson
We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. General Value Functions (GVFs) have enjoyed great success in representin…
A Self-Tuning Actor-Critic Algorithm
Tom Zahavy, Zhongwen Xu, Vivek Veeriah +5
Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well…
How Should an Agent Practice?
Janarthanan Rajendran, Richard Lewis, Vivek Veeriah +2
We present a method for learning intrinsic reward functions to drive the learning of an agent during periods of practice in which extrinsic task rewards are not available. During p…
Discovery of Useful Questions as Auxiliary Tasks
Vivek Veeriah, Matteo Hessel, Zhongwen Xu +6
Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this depart…
Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning
Alex Kearney, Vivek Veeriah, Jaden Travnik +2
There is a long history of using meta learning as representation learning, specifically for determining the relevance of inputs. In this paper, we examine an instance of meta-learn…
Many-Goals Reinforcement Learning
Vivek Veeriah, Junhyuk Oh, Satinder Singh
All-goals updating exploits the off-policy nature of Q-learning to update all possible goals an agent could have from each transition in the world, and was introduced into Reinforc…
TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent
Alex Kearney, Vivek Veeriah, Jaden B. Travnik +2
In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet fe…
Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks
Vivek Veeriah, Shangtong Zhang, Richard S. Sutton
Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, th…
Face valuing: Training user interfaces with facial expressions and reinforcement learning
Vivek Veeriah, Patrick M. Pilarski, Richard S. Sutton
An important application of interactive machine learning is extending or amplifying the cognitive and physical capabilities of a human. To accomplish this, machines need to learn a…
Differential Recurrent Neural Networks for Action Recognition
Vivek Veeriah, Naifan Zhuang, Guo-Jun Qi
The long short-term memory (LSTM) neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from…