DeepAI AI Chat
Log In Sign Up

Automata Guided Reinforcement Learning With Demonstrations

by   Xiao Li, et al.
Boston University

Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals. We propose to address these problems by combining temporal logic (TL) with reinforcement learning from demonstrations. Our method automatically generates intrinsic rewards that align with the overall task goal given a TL task specification. The policy resulting from our framework has an interpretable and hierarchical structure. We validate the proposed method experimentally on a set of robotic manipulation tasks.


page 1

page 5

page 6


Learning from Demonstrations using Signal Temporal Logic

Learning-from-demonstrations is an emerging paradigm to obtain effective...

Towards an Interpretable Hierarchical Agent Framework using Semantic Goals

Learning to solve long horizon temporally extended tasks with reinforcem...

CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

Although reinforcement learning has found widespread use in dense reward...

Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation

Visual paragraph generation aims to automatically describe a given image...

Hierarchical Decision Transformer

Sequence models in reinforcement learning require task knowledge to esti...

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Reinforcement Learning algorithms require a large number of samples to s...