Two repos to get started building reinforcement learning agents with Gym and Keras:<p><a href="https://github.com/sherjilozair/dqn" rel="nofollow">https://github.com/sherjilozair/dqn</a><p><a href="https://github.com/osh/kerlym" rel="nofollow">https://github.com/osh/kerlym</a>
The focus on improving reinforcement learning is really exciting. It's the area of machine learning that seems to have the most untapped potential.
For those more familiar in this scape - would something like this be possible for NLP? Specifically sentence classification (ie, to produce an intent with metadata)?
kudos for citing Searn, it's one of the greatest joint prediction and learning algorithms that started a whole range of useful learning to search approaches.<p>LOLS is even better. all approaches inspired by the reinforcement learning but use the information from already present data to imitate the constructed policy.<p>training neural networks with the approach of LOLS could make so many tasks reachable.<p>one could probably even imitate a komodo 9 algorithm with it.
Does anyone else think the title/url is misleading ?<p>Looking at 'Open AI', I expected a generic AI related open source project.<p>This project seems to be specifically related to "developing and comparing reinforcement learning (RL) algorithms" .... which looks like a more specific subset.