Towards Model-based Reinforcement Learning For Industry-near Environments

Abstract

Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. While these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that in practice, make these algorithms a no-go for critical operations in the industry. On the other hand, model-based reinforcement learning focuses on learning the transition dynamics between states in an environment. If these environment dynamics are adequately learned, a model-based approach is perhaps the most sample efficient method for learning agents to act in an environment optimally. The traits of model-based reinforcement are ideal for real-world environments where sampling is slow and for mission-c

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyandersen2019towards

Related papers

• Model-based Reinforcement Learning For Atari (2019)0.00
• Overcoming Model Bias For Robust Offline Deep Reinforcement Learning (2020)11.58
• PC-MLP: Model-based Reinforcement Learning With Policy Cover Guided Exploration (2021)0.00
• Towards A Simple Approach To Multi-step Model-based Reinforcement Learning (2018)0.00
• Reinforcement Learning For Robotics And Control With Active Uncertainty Reduction (2019)0.00
• Towards A Domain-specific Modelling Environment For Reinforcement Learning (2024)0.00
• Model-free Reinforcement Learning For Model-based Control: Towards Safe, Interpretable And Sample-efficient Agents (2025)0.00
• Discovering Minimal Reinforcement Learning Environments (2024)0.00