So, I’m working with Ermo on applying reinforcement learning to text based games. So, I was wondering if eventually if our method works if we could do text based learning from demonstration with reinforcement learning? Basically instead of the user pressing buttons they would describe what they wanted the system to do using english sentences.… Continue reading Natural Language LfD & RL
Bounty Hunting on a forum
Interesting, I found someone talking about bounty hunting as a non-exclusive task allocation mechanism. http://forums.ltheory.com/viewtopic.php?t=2477&p=38248
Coke Robot
So, many of the people at my robotics lab buy soda from the vending machine. They just increased the price for a drink from 1.50 to 1.75! That is paying 10.50 for a 6 pack! So, we were saying we should just buy a bunch of soda when it goes on sale. So, we of course could… Continue reading Coke Robot
Inhaler
Wow, I took my inhaler a bit ago and I feel amazing now! I think for the past few weeks I must not have been getting enough oxygen. I’ve been tired and a bit slow. For the past few weeks I have been going to the gym regularly and running/ellipticalling/lifting. So, I’ve not been kind… Continue reading Inhaler
Bounty Hunting and Cloud Robotics
Cloud robotics needs very stringent QoS guarantees and in certain cases is highly reliant on location to satisfy some of the requirements. So, I was thinking a while back that maybe a bounty hunting based cloud robotics system could work like: The robot registers with the bounty hunting service the bondsman (highly distributed might have… Continue reading Bounty Hunting and Cloud Robotics
AI and Creativity
So I just read an article stating that AI is nowhere near supplanting artists due to computers inability to “decide what is relevant”. I think that might be giving us AI researchers too much credit or going too soft on us. We have yet to develop non-noisy inputs in order to simulate the emotional and… Continue reading AI and Creativity
MAS Reading group paper
Coordinating Multi-Agent Reinforcement Learning with Limited Communication
Lentils Recipe
Lentils recipe I came up with: cooked lentils herb rice orange chicken cooked broccoli seared pear (cooked with oil and honey alongside cashews and pecans) Seasoned with cinnamon, very little nutmeg, and curry. Haven’t tried it yet but will next week hopefully. High in fiber, protein and vitamin C.
Politics and MAS
Politics seems like a good real world example of the multi-agent inverse problem and trying to get agents to coordinate at a massive (country) scale. Basically the multi-agent inverse problem is determining rules and behaviors at the low level that achieve a higher level objective. This problem is made more difficult because the low level… Continue reading Politics and MAS
Puzzle Space
I wonder what the space of problems that we consider puzzles is like. I mean how big is it? What characteristics in general do they have? Does computational complexity correspond to how difficult the puzzle is? Puzzles usually require some degree of logic. So, I’d imagine that puzzles that are most difficult correspond to those that… Continue reading Puzzle Space