We're working on sample efficient (model-based) method for solving complex planning problems using imperfect learnt model for discreet and deterministic environments with perfect information like Sokoban.
.
├── README.md (This file. Organization, road map, goals etc.)
├── doc (Papers write-ups, presentations, experiments descriptions and results etc.)
│ └── masters_thesis (PJ's master's thesis write-up)
├── etc (Other resources related to the project in general e.g. notes, papers, lectures)
└── src (All the code lives here)
├── <submodule name> (Sub-project like AlphaZero implementation)
├── checkpoints (Saved models etc.)
├── logs (All logging related files)
├── out (All side products of scripts that don't fit anywhere else)
└── script.py (All scripts performing experiments and common utils live here)
- CODE_OF_CONDUCT.md - our rules, how to behave.
- CONTRIBUTION.md - contributing guidelines, mandatory to read and apply!