Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents

2019-01-16 · Michael Cerny Green, Benjamin Sergent, Pushyami Shandilya, Vibhor Kumar

In this paper we propose a new training loop for deep reinforcement learning agents with an evolutionary generator. Evolutionary procedural content generation has been used in the creation of maps and levels for games before. Our system incorporates an evolutionary map generator to construct a training curriculum that is evolved to maximize loss within the state-of-the-art Double Dueling Deep Q Network architecture with prioritized replay. We present a case-study in which we prove the efficacy of our new method on a game with a discrete, large action space we made called Attackers and Defenders. Our results demonstrate that training on an evolutionarily-curated curriculum (directed sampling) of maps both expedites training and improves generalization when compared to a network trained on an undirected sampling of maps.

📄 PDF Abstract BibTeX arXiv:1901.05431

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Syllabus: Portable Curricula for Reinforcement Learning Agents

2024-11-18 · Ryan Sullivan, Ryan Pégoud, Ameen Ur Rahmen, Xinchen Yang 외

Curriculum learning has been a quiet yet crucial component of many of the high-profile successes of reinforcement learning. Despite this, none of the major reinforcement learning libraries directly support curriculum lea…

NetHack reinforcement-learning Reinforcement Learning

Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

2025-11-20 · Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin 외 arxiv

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution …

Reinforcement Learning Mathematical Reasoning

Proximal Curriculum for Reinforcement Learning Agents

2023-04-25 · Georgios Tzannetos, Bárbara Gomes Ribeiro, Parameswaran Kamalaruban, Adish Singla

We consider the problem of curriculum design for reinforcement learning (RL) agents in contextual multi-task settings. Existing techniques on automatic curriculum design typically require domain-specific hyperparameter t…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning

2020-03-23 · ICLR 2020 1 · Qian Long, Zihan Zhou, Abhibav Gupta, Fei Fang 외

In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large. In this paper…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Curriculum Policies for Reinforcement Learning

2018-12-01 · Sanmit Narvekar, Peter Stone

Curriculum learning in reinforcement learning is a training methodology that seeks to speed up learning of a difficult target task, by first training on a series of simpler tasks and transferring the knowledge acquired t…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning