paper-with-me

홈 › Papers

Assessing Evolutionary Terrain Generation Methods for Curriculum Reinforcement Learning

2022-03-29 · David Howard, Josh Kannemeyer, Davide Dolcetti, Humphrey Munn, Nicole Robinson

Curriculum learning allows complex tasks to be mastered via incremental progression over `stepping stone' goals towards a final desired behaviour. Typical implementations learn locomotion policies for challenging environments through gradual complexification of a terrain mesh generated through a parameterised noise function. To date, researchers have predominantly generated terrains from a limited range of noise functions, and the effect of the generator on the learning process is underrepresented in the literature. We compare popular noise-based terrain generators to two indirect encodings, CPPN and GAN. To allow direct comparison between both direct and indirect representations, we assess the impact of a range of representation-agnostic MAP-Elites feature descriptors that compute metrics directly from the generated terrain meshes. Next, performance and coverage are assessed when training a humanoid robot in a physics simulator using the PPO algorithm. Results describe key differences between the generators that inform their use in curriculum learning, and present a range of useful feature descriptors for uptake by the community.

📄 PDF Abstract BibTeX arXiv:2203.15172

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learning

2026-01-24 · Ziming Li, Chenhao Li, Marco Hutter arxiv

Curriculum learning has demonstrated substantial effectiveness in robot learning. However, it still faces limitations when scaling to complex, wide-ranging task spaces. Such task spaces often lack a well-defined difficul…

Reinforcement Learning

Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain

2026-08-17 · Rocky Liu, Tengyu Liu, Baoxiong Jia, Fangwei Zhong 외 arxiv

Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures. However, since unstructured terrain lacks explicit difficulty ordering for curriculum design, exist…

Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation

2025-03-24 · Octi Zhang, Quanquan Peng, Rosario Scalise, Bryon Boots

Developing robotic agents that can perform well in diverse environments while showing a variety of behaviors is a key challenge in AI and robotics. Traditional reinforcement learning (RL) methods often create agents that…

Continual LearningDiversityImitation LearningLifelong learning+1

TransCurriculum: Multi-Dimensional Curriculum Learning for Fast & Stable Locomotion

2026-03-14 · Prakhar Mishra, Amir Hossain Raj, Xuesu Xiao, Dinesh Manocha arxiv

High-speed legged locomotion struggles with stability and transfer losses at higher command velocities during deployment. One reason is that most curricula vary difficulty along single axis, for example increase the rang…

Guided Curriculum Learning for Walking Over Complex Terrain

2020-10-08 · Brendan Tidd, Nicolas Hudson, Akansel Cosgun

Reliable bipedal walking over complex terrain is a challenging problem, using a curriculum can help learning. Curriculum learning is the idea of starting with an achievable version of a task and increasing the difficulty…

Deep Reinforcement Learning