Investigating Enactive Learning For Autonomous Intelligent Agents

Abstract

The enactive approach to cognition is typically proposed as a viable alternative to traditional cognitive science. Enactive cognition displaces the explanatory focus from the internal representations of the agent to the direct sensorimotor interaction with its environment. In this paper, we investigate enactive learning through means of artificial agent simulations. We compare the performances of the enactive agent to an agent operating on classical reinforcement learning in foraging tasks within maze environments. The characteristics of the agents are analysed in terms of the accessibility of the environmental states, goals, and exploration/exploitation tradeoffs. We confirm that the enactive agent can successfully interact with its environment and learn to avoid unfavourable interactions using intrinsically defined goals. The performance of the enactive agent is shown to be limited by the number of affordable actions.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhadfi2018investigating

Related papers

• Life-inspired Interoceptive Artificial Intelligence For Autonomous And Adaptive Agents (2023)0.00
• Active Inference As A Model Of Agency (2024)0.00
• Autotelic Reinforcement Learning In Multi-agent Environments (2022)0.00
• Cooperative Informative Sensing For Monitoring Dynamic Indoor Environments Via Multi-agent Reinforcement Learning (2026)0.00
• An Active Learning Method For Solving Competitive Multi-agent Decision-making And Control Problems (2022)3.58
• An Efficient Open World Environment For Multi-agent Social Learning (2025)0.00
• Environment Scaling For Interactive Agentic Experience Collection: A Survey (2025)0.00
• Learning Complex Spatial Behaviours In ABM: An Experimental Observational Study (2022)0.00