31–40 of 62 posts
I'm likely completely missing the point but how is this concept of imagination different from looking ahead in a search tree? Isn't exploring a search tree like in Chess or Go exploring future possibilities and their consequences before you decide on what to do next?
I'm likely completely missing the point but how is this concept of imagination different from looking ahead in a search tree? Isn't exploring a search tree like in Chess or Go exploring future possibilities and their consequences before you decide on what to do next?
This seems to be tackling the issue of what to do when there are just too many options, and the depth of exploration necessary to make useful predictions is too high, for you to just enumerate everything, heuristically prune, and pick the optimum.
Right...
Why do we need to explicitly design architectures such as the "imagination encoder" the article describes? A proposed long term goal of deep learning is to have AI that surpasses human cognition (e.g. DeepMind's About page touts that they are "developing programs that can learn to solve any complex problem without needing to be taught how"), which was not explicitly designed in terms of architectural components such…
I'm confused. I thought AI was already about this. Are they introducing something new, or is it just gimmick and buzzwords?
https://en.wikipedia.org/wiki/Model_predictive_control Of course imagining possible outcomes before executing is useful! And it has many uses outside deep learning. No reason to reinvent new words, really. At least without referring to the established ones. Maybe there is a serious novel idea, but I've missed it. Basically, if you need to control a complex process (i.e. bring some future outcome in accordance to your…
Once you have a model, you can invert it to make a controller, as the post above points out. For classical linear models, this can be done analytically. For non-linear models, you can use the model to train a controller, running the model with random inputs to generate a training set.
(I spent several years working on the simulator problem, shipped a simulation product ("Falling Bodies", the first ragdoll simulator that didn't suck)[1] and eventually sold the technology to a physics engine startup and went on to other things. Even today, as Sony and Boston Dynamics have demonstrated at great time and expense, there's no market for legged robots yet.)
I'm likely completely missing the point but how is this concept of imagination different from looking ahead in a search tree? Isn't exploring a search tree like in Chess or Go exploring future possibilities and their consequences before you decide on what to do next?
A search tree in something like chess is quite small, and very discrete. You can enumerate every possible action, and exploring the tree to a useful depth is computationally tractable. By contrast, for an agent operating in a complex environment, like a robot in the real world, even if you somehow came up with a coherent process for listing every possible action the robot could take, you might not even be able to sto…
Are there not similar techniques to search trees that are used here? Obviously you wouldn't enumerate all options but you'd think you could guess at some practical ones then guess options between the most promising. Either way, it just feels "imagination" is making it sound like an entirely new approach when heuristically pruned search trees could be described in the same way to me.
https://en.wikipedia.org/wiki/Model_predictive_control Of course imagining possible outcomes before executing is useful! And it has many uses outside deep learning. No reason to reinvent new words, really. At least without referring to the established ones. Maybe there is a serious novel idea, but I've missed it. Basically, if you need to control a complex process (i.e. bring some future outcome in accordance to your…
I don't know if learned models are novel, but they certainly aren't vanilla MPC. (In my quick scan of them, only second paper mentions learning models)
I'm not a planning guy but I work in a closely related community so I'm a least somewhat familar with the area. Looking at the first paper ( https://arxiv.org/pdf/1707.06170.pdf ), it seems surprisingly shallow and light on details. So they have a learning system for continuous planning. So what? The AI Planning community has been doing this for ages with MDPs and POMDPs, solving problems where the planning domain ha…
This thesis from 2000 was the first hit for "reinforcement learning control theory" from google: http://www.cs.colostate.edu/~anderson/res/rl/matt-diss.pdf
BTW, people in related fields may work on similar things but don't always publish at the same venue -- labels matter. For example, ICRA and RSS are some of the top robotics venues and people trying to sell themselves as roboticists will prefer to publish there.
EDIT: In the second paper, they learn the model only from the images, not from the game state, which is neat. That should be highlighted more than the one sentence it was given.