用语言描述控制多个任务，让智能体自动组合技能完成新任务。
Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
- 通过语言编码+门控机制，动态选择或混合多个子策略。
- 在MetaWorld上成功率超基线，且无需针对每个任务重训练。
- 能组合已知技能应对未见过的任务描述和组合。
多任务强化学习常依赖任务元数据（如简短自然语言描述）来指导跨多样化目标的行为。我们提出词汇策略网络（LEXPOL），一种基于语言条件的混合策略架构，用于多任务强化学习。LEXPOL 使用文本编码器对任务元数据进行编码，并通过学习到的门控模块选择或融合多个子策略，实现跨任务的端到端训练。在 MetaWorld 基准测试中，LEXPOL 在成功率和样本效率方面达到或超过强基线，且无需任务特定的再训练。为进一步分析机制，我们研究了使用独立于门控模块获得的固定专家策略的情况，结果表明学习到的语言门控能够将这些专家组合，生成与新颖任务描述和未见任务组合相适应的行为。这些结果表明，自然语言元数据可有效索引并重组单一策略内的可复用技能。
原文摘要 · Abstract (English)
Multi-task reinforcement learning often relies on task metadata -- such as brief natural-language descriptions -- to guide behavior across diverse objectives. We present Lexical Policy Networks (LEXPOL), a language-conditioned mixture-of-policies architecture for multi-task RL. LEXPOL encodes task metadata with a text encoder and uses a learned gating module to select or blend among multiple sub-policies, enabling end-to-end training across tasks. On MetaWorld benchmarks, LEXPOL matches or exceeds strong multi-task baselines in success rate and sample efficiency, without task-specific retraining. To analyze the mechanism, we further study settings with fixed expert policies obtained independently of the gate and show that the learned language gate composes these experts to produce behaviors appropriate to novel task descriptions and unseen task combinations. These results indicate that natural-language metadata can effectively index and recombine reusable skills within a single policy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。