Empowerment -- an Introduction · HackerPapers discussions

Empowerment -- an Introduction — mentioned by bArray

Tue, 29 Apr 2025 16:23:58 GMT

From an AI perspective, I have a rough idea of what intrinsic motivation means to me: To allow an embodied agent to perform actions within an environment that would generally be considered positive, without the definition of an objective function. To break that down, to be embodied in this case is to act, sense and have some internal model that can be adapted, all operating within an environment that can be considered external to the agent. An objective function is where there is some external push towards optimality that requires knowledge of the sensors, actuators, environment, etc. A good…

Paper and discussion history. A mention is not an endorsement.

Empowerment -- an Introduction — mentioned by bArray

Wed, 31 Jul 2024 16:21:14 GMT

From an information theory perspective, it should be possible to define strategically important locations in terms of Empowerment [1]. As a map designer there are likely some rough rules you want to abide by, such as roughly equal highly empowered locations throughout the map to reduce location bias. I remember an old game where they defined map rules in FPS CTF maps that there should be more than one path to each flag (usually three) and flag areas should be partially visible from one base to another. There were lots of rules like these, some more flexible than others. [1]…

Paper and discussion history. A mention is not an endorsement.

Empowerment -- an Introduction — mentioned by bArray

Tue, 05 Jan 2021 08:57:57 GMT

There is some work that explores this from an AI perspective with relative success [1]. It turns out that you can create quite intelligent agents if they look to maximize future entropy, with interesting results [2]. It's still quite computationally expensive, but your normal search reduction tricks apply and you can get something computationally feasible. [1] https://arxiv.org/abs/1310.1863 [2] https://www.mdpi.com/1099-4300/16/5/2789

Paper and discussion history. A mention is not an endorsement.

Empowerment -- an Introduction — mentioned by bArray

Sun, 29 Nov 2020 21:40:37 GMT

I believe robotics hardware is near and damn it there, and has been for a while now. We're already seeing semi-reliable robots such as 'smart' hoovers enter homes. The biggest problem by far is the software - in particular the AI. The biggest companies in the world have thrown billions of dollars at AI, Universities have had some of the most brilliant minds among their ranks, and we essentially got some (impressive) slightly better search algorithms. There are absolute fundamental questions (+) that need to tackled in order to have the kind of generalized AI such environments require. Most AI…

Paper and discussion history. A mention is not an endorsement.

Empowerment -- an Introduction — mentioned by MrQuincle

Mon, 29 May 2017 11:52:14 GMT

Neural networks also need to balance exploration and exploitation. You will find it in the form of: + generalization / overfitting + cross-domain knowledge transfer In a more embodied approach it is free energy minimization as advocated by Friston. Consider us divided by the world through a Markov blanket, or even better consider our actions and perceptions divided by one. How do we continuously surprise ourselves without getting mad? A guy who would say it's the same thing is probably Polani with empowerment: https://arxiv.org/abs/1310.1863. The rational choice is to navigate to that…

Paper and discussion history. A mention is not an endorsement.