Inverse Reinforcement Learning
Learn about deep Q-learning and inverse reinforcement learning in the context of video games.
We'll cover the following
While the field of deep learning is independent of reinforcement learning methods such as the
Deep Q-learning
A major insight in this research was to apply a deep neural network to generate vector representations from the raw pixels of the video game rather than trying to explicitly represent some features of the “state of the game”; this neural network is the
Another key development was a technique called experience replay, wherein the history of states (here, pixels from video frames in a game), actions, and rewards is stored in a fixed-length list and re-sampled at random repeatedly, with some stochastic possibility to choose a non-optimal outcome using the epsilon-greedy approach described above. The result is that the value function updates are averaged over many samples of the same data, and correlations between consecutive samples (which could make the algorithm explore only a limited set of the solution space) are broken. Further, this “deep”
Get hands-on with 1400+ tech skills courses.