SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1707.08817 · 2017

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual interactions are used to fill a replay buffer and the sampling ratio between demonstrations and transitions is automatically tuned via a prioritized replay mechanism. Typically, carefully engineered shaping rewards are required to enable the agents to efficiently explore on high dimensional control problems such as robotics. They are also required for model-based acceleration methods relying on local solvers such as iLQG (e.g. Guided Policy Search and Normalized Advantage Function). The demonstrations replace the need for carefully engineered rewards, and reduce the exploration problem encountered by classical RL approaches in these domains. Demonstrations are collected by a robot kinesthetically force-controlled by a human demonstrator. Results on four simulated insertion tasks show that DDPG from demonstrations out-performs DDPG, and does not require engineered rewards. Finally, we demonstrate the method on a real robotics task consisting of inserting a clip (flexible object) into a rigid object.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1707.08817")
get_code_for_paper("1707.08817")
have("1707.08817")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1707.08817.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1707.08817.svg)](https://syntology.ai/paper/1707.08817)

Connect an agent — have() is free.