Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

• 类型：arxiv
• 标识：2608.01851
• 链接：https://arxiv.org/abs/2608.01851
• 主分类：multimodal
• 形态：survey
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：This survey organises the field around that axis of weights versus skills, and maps the complementary"skills"pole, from unsupervised reinforcement-learning skill discovery to large-language-model skill libraries, and shows that the word "skill" is used in at least five distinct senses.
• 待LLM分类：否
• 标题中文：Weights 还是 Skills？机器人学习方法综述：从预测动作的权重到自主编写技能的机器人
• TLDR中文：该综述围绕"权重"与"技能"这一轴线组织领域，梳理了互补的"技能"一极——从无监督强化学习的技能发现，到大语言模型的技能库——并指出"skill"一词至少存在五种不同含义。
• 来源文件：
• /inbox/tom/_candidates/2026-08-08-agent-rag-longcontext-candidates.json
• /inbox/tom/_candidates/2026-08-09-agent-rag-longcontext-candidates.json
• /inbox/tom/_candidates/2026-08-10-agent-rag-longcontext-candidates.json
• /inbox/tom/_candidates/2026-08-10-agent-memory-tool-use-candidates.json
• [S2 enrich]