Search Results for author: Levi H. S. Lelis

Found 17 papers, 8 papers with code

Program Synthesis with Best-First Bottom-Up Search

no code implementations6 Oct 2023 Saqib Ameen, Levi H. S. Lelis

In this paper, we show that current state-of-the-art cost-guided BUS algorithms suffer from a common problem: they can lose useful information given by the model and fail to perform the search in a best-first order according to a cost function.

Program Synthesis

Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks

no code implementations4 Aug 2023 Spyros Orfanos, Levi H. S. Lelis

Most of such PIRL algorithms first train a neural policy that is used as an oracle to guide the search in the programmatic space.

Translation

Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies

1 code implementation10 Jul 2023 Rubens O. Moraes, David S. Aleixo, Lucas N. Ferreira, Levi H. S. Lelis

This paper introduces Local Learner (2L), an algorithm for providing a set of reference strategies to guide the search for programmatic strategies in two-player zero-sum games.

Can You Improve My Code? Optimizing Programs with Local Search

1 code implementation10 Jul 2023 Fatemeh Abdollahi, Saqib Ameen, Matthew E. Taylor, Levi H. S. Lelis

Program Optimization with Locally Improving Search (POLIS) exploits the structure of a program, defined by its lines.

Levin Tree Search with Context Models

1 code implementation26 May 2023 Laurent Orseau, Marcus Hutter, Levi H. S. Lelis

Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node, depending on the quality of the policy.

Rubik's Cube

Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search

1 code implementation10 Aug 2022 Lucas N. Ferreira, Lili Mou, Jim Whitehead, Levi H. S. Lelis

We use Monte Carlo Tree Search as a decoding mechanism to steer the probability distribution learned by a language model towards a given emotion.

Language Modelling Music Generation

What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategies

1 code implementation22 Mar 2022 Leandro C. Medeiros, David S. Aleixo, Levi H. S. Lelis

In this paper we show that behavioral cloning can be used to learn effective sketches of programmatic strategies.

Policy-Guided Heuristic Search with Guarantees

1 code implementation21 Mar 2021 Laurent Orseau, Levi H. S. Lelis

LevinTS is guided by a policy and provides guarantees on the number of search steps that relate to the quality of the policy, but it does not make use of a heuristic function.

Computer-Generated Music for Tabletop Role-Playing Games

2 code implementations16 Aug 2020 Lucas N. Ferreira, Levi H. S. Lelis, Jim Whitehead

In this paper we present Bardo Composer, a system to generate background music for tabletop role-playing games.

speech-recognition Speech Recognition

Marginal Utility for Planning in Continuous or Large Discrete Action Spaces

no code implementations NeurIPS 2020 Zaheen Farraz Ahmad, Levi H. S. Lelis, Michael Bowling

Generating good candidate actions is critical to the success of sample-based planners, particularly in continuous or large action spaces.

Action Generation

Personalization in Human-AI Teams: Improving the Compatibility-Accuracy Tradeoff

no code implementations5 Apr 2020 Jonathan Martinez, Kobi Gal, Ece Kamar, Levi H. S. Lelis

AI systems that model and interact with users can update their models over time to reflect new information and changes in the environment.

Iterative Budgeted Exponential Search

no code implementations30 Jul 2019 Malte Helmert, Tor Lattimore, Levi H. S. Lelis, Laurent Orseau, Nathan R. Sturtevant

For graph search, A* can require $\Omega(2^{n})$ expansions, where $n$ is the number of states within the final $f$ bound.

Procedural Generation of Initial States of Sokoban

no code implementations4 Jul 2019 Dâmaris S. Bento, André G. Pereira, Levi H. S. Lelis

We propose hardness metrics based on pattern database heuristics and the use of novelty to improve the exploration of search methods in the task of generating initial states.

Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees

no code implementations7 Jun 2019 Laurent Orseau, Levi H. S. Lelis, Tor Lattimore

Under mild assumptions we prove our algorithms are guaranteed to perform only a logarithmic factor more node expansions than A* when the search space is a tree.

Asymmetric Action Abstractions for Multi-Unit Control in Adversarial Real-Time Games

no code implementations22 Nov 2017 Rubens O. Moraes, Levi H. S. Lelis

Action abstractions restrict the number of legal actions available during search in multi-unit real-time adversarial games, thus allowing algorithms to focus their search on a set of promising actions.

Cannot find the paper you are looking for? You can Submit a new open access paper.