Max Schrader

If I am get your question right, you should be able to use [ your_env.set_maxsteps(n)](https://github.com/mpSchrader/gym-sokoban/blob/master/gym_sokoban/envs/sokoban_env.py#L261). Is this what you have been looking for?

It might be a bug, that the parameter is not set properly. Where did you try to change it? There are different environment definitions in [./gym_sokoban/envs/sokoban_env_variations.py](https://github.com/mpSchrader/gym-sokoban/blob/e0cdb6102bccccef4c6606d6843986e03ecf9a21/gym_sokoban/envs/sokoban_env_variations.py#L15).

Hey, I did not develop a baseline agent my self. I would recommend, comparing your result with the results in the I2A Deep Mind Paper. If you have your results...

Hey, Currently I do not have any reliable success rates my self. I would recommend reading Deep Minds paper about I[magination Augmented Agents](https://papers.nips.cc/paper/7152-imagination-augmented-agents-for-deep-reinforcement-learning). In there they represanted results and compared...

This weekend I will have a look the openAIs [baselines repo](https://github.com/openai/baselines) and check on how to make gym-sokoban usable in with the repo. After that I will upload some baselines...

@Olloxan Thanks for the hint. I was planning to first run the simple subpackages from https://github.com/openai/baselines#subpackages-1 as a very first baseline and later on try more advanced techniques. ;-) Maybe...

Hi @wrongbattery, This is currently due to the Level Generation, which generates always solvable environment. The generation algorithm uses a Depth-First-Search to generate the room, by reverse playing the initial...

Hi @Olloxan, thanks for your insights. Regarding the pixel size did you scaled it down or did you used the tiny_world rendering modes? Do you have some results to share?...

Awesome! I am looking forward to reading your thesis.

Hey, Thanks for that input. Could you open a new ticket for the issue of failing room generation? I already got an idea on how to fix this issue. By...