Generative Adversarial Imagination For Sample Efficient Deep Reinforcement Learning

Abstract

Reinforcement learning has seen great advancements in the past five years. The successful introduction of deep learning in place of more traditional methods allowed reinforcement learning to scale to very complex domains achieving super-human performance in environments like the game of Go or numerous video games. Despite great successes in multiple domains, these new methods suffer from their own issues that make them often inapplicable to the real world problems. Extreme lack of data efficiency, together with huge variance and difficulty in enforcing safety constraints, is one of the three most prominent issues in the field. Usually, millions of data points sampled from the environment are necessary for these algorithms to converge to acceptable policies. This thesis proposes novel Generative Adversarial Imaginative Reinforcement Learning algorithm. It takes advantage of the recent introduction of highly effective generative adversarial models, and Markov property that underpins re

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykielak2019generative

Related papers

• Generative Adversarial Exploration For Reinforcement Learning (2022)0.00
• Gan-based Intrinsic Exploration For Sample Efficient Reinforcement Learning (2022)2.26
• Enhanced Experience Replay Generation For Efficient Reinforcement Learning (2017)0.00
• From Generative To Episodic: Sample-efficient Replicable Reinforcement Learning (2025)0.00
• Enhancing Data Efficiency In Reinforcement Learning: A Novel Imagination Mechanism Based On Mesh Information Propagation (2023)2.29
• Sample Efficient Reinforcement Learning Via Model-ensemble Exploration And Exploitation (2021)0.00
• Genai-based Multi-agent Reinforcement Learning Towards Distributed Agent Intelligence: A Generative-rl Agent Perspective (2025)0.00
• Breaking The Sample Size Barrier In Model-based Reinforcement Learning With A Generative Model (2020)9.03