Probing Transfer In Deep Reinforcement Learning Without Task Engineering

Abstract

We evaluate the use of original game curricula supported by the Atari 2600 console as a heterogeneous transfer benchmark for deep reinforcement learning agents. Game designers created curricula using combinations of several discrete modifications to the basic versions of games such as Space Invaders, Breakout and Freeway, making them progressively more challenging for human players. By formally organising these modifications into several factors of variation, we are able to show that Analyses of Variance (ANOVA) are a potent tool for studying the effects of human-relevant domain changes on the learning and transfer performance of a deep reinforcement learning agent. Since no manual task engineering is needed on our part, leveraging the original multi-factorial design avoids the pitfalls of unintentionally biasing the experimental setup. We find that game design factors have a large and statistically significant impact on an agent's ability to learn, and so do their combinatorial intera

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrusu2022probing

Related papers

• Visual Transfer Between Atari Games Using Competitive Reinforcement Learning (2018)7.50
• Enhancing Two-player Performance Through Single-player Knowledge Transfer: An Empirical Study On Atari 2600 Games (2024)0.00
• Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay (2016)0.00
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Is Deep Reinforcement Learning Really Superhuman On Atari? Leveling The Playing Field (2019)0.00