MDP models are determined by the agent architecture and the environmental dynamics

📖 Description

[*Seeking Power is Often Robustly Instrumental in MDPs*](https://www.lesswrong.com/posts/6DuJxY8X45Sco4bS2/seeking-power-is-often-robustly-instrumental-in-mdps) relates the structure of the agent's environment (the 'Markov decision process (MDP) model') to the tendencies of optimal policies for different reward functions in that environment ('instrumental convergence'). The results tell us what optimal decision-making 'tends to look like' in a given environment structure, formalizing reasoning that says e.g. that most agents stay alive because that helps them achieve their goals.

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/XkXL96H6GknCbT5QH/mdp-models-are-determined-by-the-agent-architecture-and-the