Continual Reinforcement Learning In 3D Non-stationary Environments

Abstract

High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observations space. However, in real world settings, the environment is often non-stationary and subject to unpredictable, frequent changes. In this paper we propose and openly release CRLMaze, a new benchmark for learning continually through reinforcement in a complex 3D non-stationary task based on ViZDoom and subject to several environmental changes. Then, we introduce an end-to-end model-free continual reinforcement learning strategy showing competitive results with respect to four different baselines and not requiring any access to additional supervised signals, previously encountered environmental conditions or observations.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylomonaco2019continual

Related papers

• From Two-dimensional To Three-dimensional Environment With Q-learning: Modeling Autonomous Navigation With Reinforcement Learning And No Libraries (2024)0.00
• Demonstration-guided Continual Reinforcement Learning In Dynamic Environments (2025)0.00
• Continual Visual Reinforcement Learning With A Life-long World Model (2023)2.26
• Learning To Design Games: Strategic Environments In Reinforcement Learning (2017)0.00
• Continual Reinforcement Learning By Planning With Online World Models (2025)0.00
• Safe Continual Reinforcement Learning In Non-stationary Environments (2026)12.89
• Hierarchical Reinforcement Learning In Complex 3D Environments (2023)0.00
• Context-aware Safe Reinforcement Learning For Non-stationary Environments (2021)9.76