SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.08027 · 2019

Self-Attentional Credit Assignment for Transfer in Reinforcement Learning

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

The ability to transfer knowledge to novel environments and tasks is a sensible desiderata for general learning agents. Despite the apparent promises, transfer in RL is still an open and little exploited research area. In this paper, we take a brand-new perspective about transfer: we suggest that the ability to assign credit unveils structural invariants in the tasks that can be transferred to make RL more sample-efficient. Our main contribution is SECRET, a novel approach to transfer learning for RL that uses a backward-view credit assignment mechanism based on a self-attentive architecture. Two aspects are key to its generality: it learns to assign credit as a separate offline supervised process and exclusively modifies the reward function. Consequently, it can be supplemented by transfer methods that do not modify the reward function and it can be plugged on top of any RL algorithm.

For agents

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

get_harvested_code_for_paper("1907.08027")
get_code_for_paper("1907.08027")
have("1907.08027")

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

curl https://syntology.ai/api/ran/1907.08027.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.08027.svg)](https://syntology.ai/paper/1907.08027)

Connect an agent — have() is free.