arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.01655cs.LG
收藏

强化学习中高效的Transformers算法

Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation

Carnegie Mellon University(卡内基梅隆大学)

Emilio Parisotto, Ruslan Salakhutdinov

摘要:

许多现实世界的应用,如机器人技术,提供了对功率和计算的硬约束,这限制了强化学习(RL)代理的可行模型复杂性。类似地,在许多分布式RL设置中,操作是在未加速的硬件(如CPU)上完成的,这同样限制了模型大小,以防止棘手的实验运行时间。这些“行为者-延迟”约束设置对模型复杂性的扩展提出了主要障碍,该模型复杂性最近在监督学习中非常成功。为了能够利用大的模型容量,同时仍然在系统施加的限制内操作,在代理期间,我们开发了一个“演员-学习者蒸馏”(ALD)的程序,利用连续形式的蒸馏,将学习进度从大容量的学习者模型转移到小容量的演员模型。作为一个案例研究,我们开发了这个程序的上下文中的部分可观察的环境,其中Transformer模型有很大的改进LSTM最近,在成本显着更高的计算复杂性。使用Transformer模型作为学习者,LSTM作为演员,我们在几个具有挑战性的记忆环境中证明,使用演员-学习者蒸馏恢复了Transformer学习者模型的明显样本效率增益,同时保持了快速推理并减少了LSTM演员模型的总训练时间。

英文摘要:

Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These "actor-latency" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within the limits imposed by the system during acting, we develop an "Actor-Learner Distillation" (ALD) procedure that leverages a continual form of distillation that transfers learning progress from a large capacity learner model to a small capacity actor model. As a case study, we develop this procedure in the context of partially-observable environments, where transformer models have had large improvements over LSTMs recently, at the cost of significantly higher computational complexity. With transformer models as the learner and LSTMs as the actor, we demonstrate in several challenging memory environments that using Actor-Learner Distillation recovers the clear sample-efficiency gains of the transformer learner model while maintaining the fast inference and reduced total training time of the LSTM actor model.

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。

↑