arxivst stuff from arxiv that you should probably bookmark

One-Shot Imitation Learning for Robots—Learn More with Less Data

Post · Mar 22, 2017 20:57 ·

reinforcement learning one-shot

Using a soft attention mechanism and a novel training method, you can create an RL agent that can learn from a few demonstartions of a task and then perform variants of that task!

Arxiv Abstract

  • Yan Duan
  • Marcin Andrychowicz
  • Bradly Stadie
  • Jonathan Ho
  • Jonas Schneider
  • Ilya Sutskever
  • Pieter Abbeel
  • Wojciech Zaremba

Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we call one-shot imitation learning. Specifically, we consider the setting where there is a very large set of tasks, and each task has many instantiations. For example, a task could be to stack all blocks on a table into a single tower, another task could be to place all blocks on a table into two-block towers, etc. In each case, different instances of the task would consist of different sets of blocks with different initial states. At training time, our algorithm is presented with pairs of demonstrations for a subset of all tasks. A neural net is trained that takes as input one demonstration and the current state (which initially is the initial state of the other demonstration of the pair), and outputs an action with the goal that the resulting sequence of states and actions matches as closely as possible with the second demonstration. At test time, a demonstration of a single instance of a new task is presented, and the neural net is expected to perform well on new instances of this new task. The use of soft attention allows the model to generalize to conditions and tasks unseen in the training data. We anticipate that by training this model on a much greater variety of tasks and settings, we will obtain a general system that can turn any demonstrations into robust policies that can accomplish an overwhelming variety of tasks. Videos available at

Read the paper (pdf) »