Reinforcement learning is a paradigm that will eventually be superseded. We just haven't figured out what the new, more generally useful, paradigm is yet. When we do, there's going to be a revolution. It will be very interesting.
Show this thread
-
It's really about the problem formulation. I think it's holding us back.
The algos are inadequate to address the problem formulation, and the problem is misleading & counter-productive (in particular reward maximization, static separation between agent & environment, lack of distinction between behavior programs & behavior program generation)
-
-
@fchollet please say more about your last two items: Why is separation between the agent and the environment a problem? What is the distinction between behavior programs and behavior program generation that we need? -
1) An agent is not a static set of possible actions and reward variables. Its affordances change over time: the environment becomes part of the agent. A clever agent will actively seek to gradually *own (absorb) more of the environment* over time.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.