-
### Expected behavior
Universe-starter-agent learns neonrace using:
```
python train.py --num-workers 4 --env-id flashgames.NeonRace-v0 --log-dir /tmp/neonrace -m child
```
### Actual behavio…
-
Dear Danny
Thank you for the great work! I have two questions:
**1- Is it possible to change the “CliffWalk Actor Critic Solution.ipynb” code to implement Actor-Critic for Gym Arari games?**
I b…
-
I'm starting to work on a framework for reinforcement learning in https://github.com/tbreloff/Reinforce.jl, and I was thinking it would be nice to include the core abstractions in LearnBase so that I …
-
(First, please check https://github.com/openai/universe/wiki/Solutions-to-common-problems for solutions to many common problems)
### Expected behavior
Expected demo app to open and run the game
…
-
Interesting paper http://arxiv.org/abs/1604.06057 that tackles Montezuma's revenge, where Dqn does not work at all because of the delayed sparse rewards, it requires a longer strategy to be followed w…
-
(First, please check https://github.com/openai/universe/wiki/Solutions-to-common-problems for solutions to many common problems)
### Expected behavior
I am running an Ubuntu 16.04 machine on AWS…
-
Firstly, I like to thank everyone involved with this project - I believe this has potential to really speed up machine/reinforcement learning progress.
As far as I can tell, this project focuses pred…
-
The default random number generator of numpy seems to be used throughout the code (`grep np.random`). For example in: [mountain_car.py](https://github.com/openai/gym/blob/master/gym/envs/classic_contr…
-
1 Education
Unite4.org will connect PEOPLE with local charities spanning all levels of education. These organizations strengthen their communities by providing positive, collaborative environments …