Model-based Reinforcement Learning For Atari

Abstract

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How can people learn so quickly? Part of the answer may be that people can learn how the game works and predict which actions will lead to desirable outcomes. In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with fewer interactions than model-free methods. We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting. Our experiments evaluate SimPLe on a range of Atari games in low data regime of 100k interactions between the agent and the environment,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykaiser2019model

Related papers

• Playing Atari With Six Neurons (2018)0.00
• Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay (2016)0.00
• Explaining Deep Reinforcement Learning Agents In The Atari Domain Through A Surrogate Model (2021)0.00
• Driving Reinforcement Learning With Models (2019)0.00
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00
• Fast Exploration With Simplified Models And Approximately Optimistic Planning In Model Based Reinforcement Learning (2018)0.00
• Towards Model-based Reinforcement Learning For Industry-near Environments (2019)5.84
• Importance Of Using Appropriate Baselines For Evaluation Of Data-efficiency In Deep Reinforcement Learning For Atari (2020)0.00