Gotta Learn Fast: A New Benchmark for Generalization in RL

04/10/2018
by   Alex Nichol, et al.
0

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.

READ FULL TEXT

page 3

page 7

research
09/16/2020

Transfer Learning in Deep Reinforcement Learning: A Survey

This paper surveys the field of transfer learning in the problem setting...
research
11/14/2018

Natural Environment Benchmarks for Reinforcement Learning

While current benchmark reinforcement learning (RL) tasks have been usef...
research
12/05/2019

Training Agents using Upside-Down Reinforcement Learning

Traditional Reinforcement Learning (RL) algorithms either predict reward...
research
04/22/2019

Transfer and Online Reinforcement Learning in STT-MRAM Based Embedded Systems for Autonomous Drones

In this paper we present an algorithm-hardware codesign for camera-based...
research
12/03/2019

Leveraging Procedural Generation to Benchmark Reinforcement Learning

In this report, we introduce Procgen Benchmark, a suite of 16 procedural...
research
11/27/2022

Combined Peak Reduction and Self-Consumption Using Proximal Policy Optimization

Residential demand response programs aim to activate demand flexibility ...
research
12/28/2017

Reinforcement Learning with Analogical Similarity to Guide Schema Induction and Attention

Research in analogical reasoning suggests that higher-order cognitive fu...

Please sign up or login with your details

Forgot password? Click here to reset