takuseno / d3rlpy

Hi,

I'm trying to integrate a model-based RL algorithm to the d3rlpy library but couldn't find any documentation to know where & how to begin. Would really appreciate if you could please point me where to look and maybe the specific steps?

Currently, there is no documentation for users to implement their own algorithms yet. I'd love to make one though... One thing I can propose is to directly modify base RL algorithms. For example, if your new algorithm is based on SAC, I suggest you to directly edit these files:

d3rlpy/d3rlpy/algos/qlearning/sac.py

Line 29 in cb2f771

class SACConfig(LearnableConfig):

d3rlpy/d3rlpy/algos/qlearning/torch/sac_impl.py

Line 49 in cb2f771

class SACImpl(DDPGBaseImpl):

d3rlpy/d3rlpy/algos/qlearning/torch/ddpg_impl.py

Line 49 in cb2f771

class DDPGBaseImpl(

I have added an example to create your own algorithm:
https://github.com/takuseno/d3rlpy/blob/master/examples/custom_algo.py

Once you implement your own algorithm, you can leverage all functionalities that d3rlpy provides.

Please let me close this issue because this is the best thing I can provide for now.

[QUESTION] Adding a new algorithm to d3rlpy