Two things that could very well come out of misunderstandings of the material:
If we have an agent whose actions affect future observations, why can’t we think of information about the agent’s embedding in the environment as being encoded in its observations? For example, in the heating-up game, we could imagine a computer that has sensors that detect heat emanating from its hardware, and that the data from those sensors is incorporated into the input stream of observations of the “environment”. The agent could then learn from past experience that certain actions lead to certain patterns of observations, which correspond to what people seem to mean when they say that it is giving
Two things that could very well come out of misunderstandings of the material:
... (read 449 more words →)If we have an agent whose actions affect future observations, why can’t we think of information about the agent’s embedding in the environment as being encoded in its observations? For example, in the heating-up game, we could imagine a computer that has sensors that detect heat emanating from its hardware, and that the data from those sensors is incorporated into the input stream of observations of the “environment”. The agent could then learn from past experience that certain actions lead to certain patterns of observations, which correspond to what people seem to mean when they say that it is giving