paper-with-me

Papers

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

2022-03-22 · 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. We show that even the sketches learned by cloning the behavior of weak players can help the synthesis of programmatic strategies. This is because even weak players can provide helpful information, e.g., that a player must choose an action in their turn of the game. If behavioral cloning is not employed, the synthesizer needs to learn even the most basic information by playing the game, which can be computationally expensive. We demonstrate empirically the advantages of our sketch-learning approach with simulated annealing and UCT synthesizers. We evaluate our synthesizers in the games of Can't Stop and MicroRTS. The sketch-based synthesizers are able to learn stronger programmatic strategies than their original counterparts. Our synthesizers generate strategies of Can't Stop that defeat a traditional programmatic strategy for the game. They also synthesize strategies that defeat the best performing method from the latest MicroRTS competition.

📄 PDF Abstract BibTeX arXiv:2203.11912

Code (1)

leandrocouto/sketch-learning 공식 구현

Similar Papers 제목 키워드 기반

Controllable Text-to-Image Generation with GPT-4

2023-05-29 · Tianjun Zhang, Yi Zhang, Vibhav Vineet, Neel Joshi 외

Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkabl…

Image GenerationInstruction FollowingSpatial ReasoningText to Image Generation+1

Programmatic Reinforcement Learning: Navigating Gridworlds

2024-02-18 · Guruprerana Shabadi, Nathanaël Fijalkow, Théo Matricon

The field of reinforcement learning (RL) is concerned with algorithms for learning optimal policies in unknown stochastic environments. Programmatic RL studies representations of policies as programs, meaning involving h…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play

2026-05-16 · Roger Creus Castanyer, Geoffrey Bradway, Lorenz Wolf, Maxwill Lin 외 arxiv

We introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs. Teachers and students are specialised LoRA adapters on a shared fr…

Reinforcement Learning

Deep Generation of Face Images from Sketches

2020-06-01 · Shu-Yu Chen, Wanchao Su, Lin Gao, Shihong Xia 외

Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend to overfit to sketches, thus requiring professional sketches or even edge ma…

Image-to-Image TranslationTranslation

Law of the Weakest Link: Cross Capabilities of Large Language Models

2024-09-30 · Ming Zhong, Aston Zhang, Xuewei Wang, Rui Hou 외

The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are …