Gotta Learn Fast: A New Benchmark for Generalization in RL

TL;DR

This paper introduces a new RL benchmark based on Sonic the Hedgehog to evaluate transfer and few-shot learning algorithms, providing a standardized way to measure generalization in reinforcement learning.

Contribution

It presents a novel Sonic-based benchmark for RL, along with baseline evaluations to facilitate future research on transfer and few-shot learning.

Findings

Baseline algorithms show varying performance on the new benchmark.

The benchmark effectively measures transfer learning capabilities.

Initial results highlight challenges in generalization in RL.

Abstract

In this report, we present a new reinforcement learning (RL) benchmark based on the Sonic the Hedgehog (TM) video game franchise. This benchmark is intended to measure the performance of transfer learning and few-shot learning algorithms in the RL domain. We also present and evaluate some baseline algorithms on the new benchmark.