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 2402.13201cs.ROcs.AIcs.LG
收藏

使用决策变换器实现四足运动的微型强化学习

Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers

Harvard University(哈佛大学)

Orhan Eren Akgün, Néstor Cuevas, Matheus Farias, Daniel Garces

AI总结:

本文提出用决策变换器结合专家演示与自定义奖励进行模仿学习,并通过量化和剪枝压缩模型,使四足机器人Bittle在资源受限平台上实现自然步态且模型体积减少约30%。

摘要:

资源受限的机器人平台对于需要低成本硬件替代方案的任务特别有用,例如在搜救应用中存在丢失机器人的风险,或在群体机器人技术中需要大量设备。因此,找到将强化学习技术适配到这些超低成本机器人平台所施加的较低计算能力和较小内存容量限制的机制至关重要。我们尝试通过提出一种使模仿学习可部署到资源受限机器人平台的方法来满足这一需求。在此,我们将模仿学习问题建模为条件序列建模任务,并使用带有自定义奖励增强的专家演示来训练决策变换器(Decision Transformer)。然后,我们使用包括量化和剪枝在内的软件优化方案来压缩所得到的生成模型。我们在 Isaac Gym 中通过仿真测试了我们的方法,Isaac Gym 是一个为强化学习设计的逼真物理仿真环境。我们通过实验证明,我们的方法为 Bittle(一种资源受限的四足机器人)实现了外观自然的步态。我们还进行了多次仿真,以展示剪枝和量化对模型性能的影响。我们的结果表明,量化(低至 4 位)和剪枝将模型大小减少了约 30%,同时保持了具有竞争力的奖励,使模型能够部署在资源受限的系统中。

英文摘要:

Resource-constrained robotic platforms are particularly useful for tasks that require low-cost hardware alternatives due to the risk of losing the robot, like in search-and-rescue applications, or the need for a large number of devices, like in swarm robotics. For this reason, it is crucial to find mechanisms for adapting reinforcement learning techniques to the constraints imposed by lower computational power and smaller memory capacities of these ultra low-cost robotic platforms. We try to address this need by proposing a method for making imitation learning deployable onto resource-constrained robotic platforms. Here we cast the imitation learning problem as a conditional sequence modeling task and we train a decision transformer using expert demonstrations augmented with a custom reward. Then, we compress the resulting generative model using software optimization schemes, including quantization and pruning. We test our method in simulation using Isaac Gym, a realistic physics simulation environment designed for reinforcement learning. We empirically demonstrate that our method achieves natural looking gaits for Bittle, a resource-constrained quadruped robot. We also run multiple simulations to show the effects of pruning and quantization on the performance of the model. Our results show that quantization (down to 4 bits) and pruning reduce model size by around 30\% while maintaining a competitive reward, making the model deployable in a resource-constrained system.

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。

↑