生存强化学习：迈向可扩展的自监督强化学习
Survival Reinforcement Learning: Toward Scalable Self-Supervised RL
AI总结：
提出生存强化学习（SRL），一种基于在线分类的方法，通过最大化智能体在目标状态停留时间来解决对比强化学习中的均匀性-容忍性困境，在长时程运动任务上性能提升2至8倍。
摘要：
虽然自监督对比强化学习（CRL）展现了显著的深度扩展能力，成功使用了超过64层的网络，但由于对比损失固有的均匀性-容忍性困境，扩展的CRL在长时程目标条件规划中仍然存在困难。我们引入了生存强化学习（SRL），一种基于在线分类的替代方法，通过最大化智能体在目标状态的停留时间来扩展生存价值学习框架。SRL绕过了CRL的结构约束，并缓解了生存框架固有的“bang-bang”控制解，这种控制解在复杂动态系统中往往引发不良行为。在多种机器人基准测试中，扩展的SRL在操作任务上与最先进的CRL相当，并在稳定的长时程运动任务上性能提升2至8倍。我们的结果提供了强有力的额外证据，表明基于分类的方法可能成为扩展强化学习这一更广泛努力中的关键原语。
英文摘要：
While self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities, successfully using networks over 64 layers, scaled CRL still struggles with long-horizon goal-conditioned planning due to the uniformity-tolerance dilemma inherent in contrastive losses. We introduce Survival Reinforcement Learning (SRL), an online classification-based alternative that extends the survival value learning framework by maximizing the agent's dwell time at target goals. SRL bypasses the structural constraints of CRL and mitigates the "bang-bang" control solutions inherent to survival frameworks, which often induce undesirable behavior in complex dynamical systems. Evaluated across diverse robotic benchmarks, scaled SRL matches state-of-the-art CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks. Our results provide strong additional evidence that classification-based methods may serve as a key primitive in the broader effort to scale reinforcement learning and an open-source implementation is available online: https://github.com/Simple-Robotics/survival-reinforcement-learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
