Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay

Abstract

This paper introduces a novel method for learning how to play the most difficult Atari 2600 games from the Arcade Learning Environment using deep reinforcement learning. The proposed method, human checkpoint replay, consists in using checkpoints sampled from human gameplay as starting points for the learning process. This is meant to compensate for the difficulties of current exploration strategies, such as epsilon-greedy, to find successful control policies in games with sparse rewards. Like other deep reinforcement learning architectures, our model uses a convolutional neural network that receives only raw pixel inputs to estimate the state value function. We tested our method on Montezuma's Revenge and Private Eye, two of the most challenging games from the Atari platform. The results we obtained show a substantial improvement compared to previous learning approaches, as well as over a random player. We also propose a method for training deep reinforcement learning agents using huma

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhosu2016playing

Related papers

• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00
• Playing Atari With Six Neurons (2018)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• Model-based Reinforcement Learning For Atari (2019)0.00
• Visual Transfer Between Atari Games Using Competitive Reinforcement Learning (2018)7.50
• Probing Transfer In Deep Reinforcement Learning Without Task Engineering (2022)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Enhancing Two-player Performance Through Single-player Knowledge Transfer: An Empirical Study On Atari 2600 Games (2024)0.00