Issues
- 0
- 0
Rendering Issue while training
#94 opened by brunoleej - 7
Doesn't work on Python 3.12 or 3.11
#92 opened by timoklein - 4
- 0
Automate version upgrade
#89 opened by epignatelli - 0
Pull key out of the `State`, use external `key` in the `Environment.step` function
#70 opened by epignatelli - 0
CD docs currently fails to update the website if there is an existing website
#81 opened by epignatelli - 0
- 2
Agents walking through walls/lava?
#82 opened by danieljarne - 0
Add documentation
#63 opened by epignatelli - 0
Setup website
#55 opened by epignatelli - 0
- 0
Improve readme
#58 opened by epignatelli - 0
Run baselines
#56 opened by epignatelli - 0
Add hparam search example
#57 opened by epignatelli - 0
Speed up logging
#60 opened by epignatelli - 1
Create a document to link the code functions with the mathematical formalisms and conventions (e.g., reward is a function of state, action, next_state)
#36 opened by epignatelli - 0
tasks now take 3 parameters R(s, a, s'), which makes the reward function non-Markovian
#48 opened by epignatelli - 2
Is this still under development ?
#52 opened by MathisFederico - 0
Implement more environments
#10 opened by epignatelli - 1
Improve graphics and tiles
#15 opened by epignatelli - 1
Batch the player entity to prepare the way to have multi-agent environments
#20 opened by epignatelli - 1
- 1
Broken link
#37 opened by astanziola - 0
- 0
Rendering two sprites in the same cell
#34 opened by epignatelli - 1
Make components truly composable
#26 opened by epignatelli - 0
- 1
`KeyDoor`: make room sizes variable
#18 opened by epignatelli - 0
- 0
Fix color chart
#22 opened by epignatelli - 1
Add a way to compose reward functions
#11 opened by epignatelli