Dreamer has the ability to rely on what they have learned to predict the outcome for problems they’ve never encountered before. From that, which they can give an exact solution.
Recently, researchers from Google’s DeepMind project collaborated with the University of Toronto with an AI project called ‘Dreamer’. It aims to test the effectiveness of augmented learning on artificial intelligence.
According to the researchers, the initial results of the Dreamer project show that this artificial intelligence is very effective in processing data. As well as it has quite good performance in computing and processing – compared to previous AI approaches.
Basically, Dreamer uses an operational model with a complex multi-part structure. A part of the system that encodes the observations as well as the actions of the system. Another part will predict the resulting states of the problem to be solved.
The third part will give an assessment of the status of the problem, then based on this result to make a learning plan for the system. In their experiments, the researchers tested the Dreamer system on 20 exercises in the simulator.
The result they achieved is that Dreamer took an average of 9 hours to achieve results 106 steps. According to the researchers, AI Dreamer is effective in using available models to accurately predict what they need to do to solve problems.
Not only that, but Dreamer is also effective for short-term plans, when comparing the results of 20 exercises with the old AI. Dreamer completed 16/20 faster, and achieved a tie in the remaining 4 exercises. If you are an AI researcher and curious about this project, the source code of Dreamer is currently publicly posted on the project’s Github page.