Learning Time-Sensitive Strategies in Space Fortress

by   Akshat Agarwal, et al.

Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL. These include reward sparsity, abrupt context-dependent reversals of strategy and time-sensitive game play. In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable of learning. Then, we present our enhancements to an existing algorithm and show big performance increases through each enhancement through an ablation study. We discuss how each of these enhancements was able to help and also argue that appropriate transfer learning boosts performance.


Challenges of Context and Time in Reinforcement Learning: Introducing Space Fortress as a Benchmark

Research in deep reinforcement learning (RL) has coalesced around improv...

Gotta Learn Fast: A New Benchmark for Generalization in RL

In this report, we present a new reinforcement learning (RL) benchmark b...

Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari

Evolution Strategies (ES) have recently been demonstrated to be a viable...

Generalization in Deep RL for TSP Problems via Equivariance and Local Search

Deep reinforcement learning (RL) has proved to be a competitive heuristi...

Transfer Learning for Operator Selection: A Reinforcement Learning Approach

In the past two decades, metaheuristic optimization algorithms (MOAs) ha...

Deep Reinforcement Learning using Capsules in Advanced Game Environments

Reinforcement Learning (RL) is a research area that has blossomed tremen...

Reinforcement Learning with Brain-Inspired Modulation can Improve Adaptation to Environmental Changes

Developments in reinforcement learning (RL) have allowed algorithms to a...