DeepAI AI Chat
Log In Sign Up

Hierarchical Few-Shot Imitation with Skill Transition Models

07/19/2021
by   Kourosh Hakhamaneshi, et al.
berkeley college
0

A desirable property of autonomous agents is the ability to both solve long-horizon problems and generalize to unseen tasks. Recent advances in data-driven skill learning have shown that extracting behavioral priors from offline data can enable agents to solve challenging long-horizon tasks with reinforcement learning. However, generalization to tasks unseen during behavioral prior training remains an outstanding challenge. To this end, we present Few-shot Imitation with Skill Transition Models (FIST), an algorithm that extracts skills from offline data and utilizes them to generalize to unseen tasks given a few downstream demonstrations. FIST learns an inverse skill dynamics model, a distance function, and utilizes a semi-parametric approach for imitation. We show that FIST is capable of generalizing to new tasks and substantially outperforms prior baselines in navigation experiments requiring traversing unseen parts of a large maze and 7-DoF robotic arm experiments requiring manipulating previously unseen objects in a kitchen.

READ FULL TEXT
08/11/2021

Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback

A promising approach to solving challenging long-horizon tasks has been ...
09/19/2022

Latent Plans for Task-Agnostic Offline Reinforcement Learning

Everyday tasks of long-horizon and comprising a sequence of multiple imp...
02/13/2020

Adapting to Unseen Environments through Explicit Representation of Context

In order to deploy autonomous agents to domains such as autonomous drivi...
05/16/2022

Generalizing to New Tasks via One-Shot Compositional Subgoals

The ability to generalize to previously unseen tasks with little to no s...
06/18/2020

Generalization of Agent Behavior through Explicit Representation of Context

In order to deploy autonomous agents in digital interactive environments...
02/28/2022

LISA: Learning Interpretable Skill Abstractions from Language

Learning policies that effectually utilize language instructions in comp...