coach
coach copied to clipboard
IntelLabs
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Is there any example code / tutorial demonstrating how I can use e.g. UCB Exploration via Q-Ensembles together with the rest of the pieces of the library?
Hi, I am a Phd student and I want to use our university cluster to do distributed learning. Our university does not allow use of Docker because of security issues....
I encountered a strange behavior. For ClippedPPO, PPO and ActorCritic I was not able to get the signals defined in there init-Method. Loss, Gradients, Likelihood, KL Divergence, etc... I'm not...
I already have the structure and weights for an image autoencoder. Should I do this as a InputFilter or a Input Embedder? How should I go about doing this?
I am trying to make a simple BC experiment using RL-Coach and a custom Gym environment. Based on the idea of [this](https://datascience.stackexchange.com/questions/36453/multivariable-time-series-forecast-with-nn-vs-rnn) I am trying to predict the target variable...
Hi I'm building a new gym that needs a simple 'board' to record the game status, eg. 10x10 cells, and the agent position. Unfortunately I'm unable to figure out how...
Hi, I see the starcraft example can use the CompoundActionSpace, but are there any examples of how the agent should be configured? It's unclear to me what presets should support...
Great work here! So I am trying to use my own Carla driving_benchmark with a specific town, pose and vehicle/pedestrian parameters or at least use the basic_experiment_suit found in Carla's...
Is there an integration with wandb? It's really nice to see all results in one place. E.g. https://docs.wandb.com/library/integrations/ray-tune Thanks!