#This submission is deprecated, please ignore it.
This is a simple convolutional network implementation that fits all atari games within the OpenAI Gym. It was implemented using AgentNet library in ~3 hours and trained on my colleague's GPU over ~4 hours All the details can be found
- SpaceInvaders here (stopped after 5, still not converged)
- AirRaid (stopped after 1k) in this notebook
Greetings! We happen to have just pushed into the open source one of the Lasagne-based library for reinforcement learning algorithm design.
- The repo's here: AgentNet
- The simple-stupid CNN demo for Atari SpaceInvaders
- The same notebook that works trains weaker dense network for SpaceInvaders
- This is better if you have no GPU
- Some tinkering with SpaceInvaders
On the bright side,
- it is capable of sustaining virtually any custom RL (and even non-RL) architecture using minimalistic Lasagne network design
- it has most of the generic reinforcement learning algorithms (Q-learning, K-step algos, SARSA, Advantage Actor-Critic)
- It is also capable of interacting with any external environment with a simple wrapper.
On the gloomy one, it has been made public ~4 days ago and doesn't have a community yet. Prior to that, it's only been used by several Yandex researchers for tinkering.
I would very much like to provide a set of baseline training/testing stands for several problems (and i will do so shortly), for people to be able to experiment with NN architecture, but i'm a bit doubtful about
- whether the interface of the library doesn't have any flaws worth immediate fixing
- whether there is someone interested in tinkering with openai baselines, provided they're readable and performing reasonably.
The most basic Reinforcement Learning pipeline looks like this
The questions are, again, if there is anyone interested in having such baselines for gym problems, and if so, what are possible api improvements you would recommend?
Could you produce a single entry file and a single command to start training. This would make reproduction way easier.