mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-18 09:54:10 +00:00
Update todos
This commit is contained in:
parent
6c423add8d
commit
233f346d53
3 changed files with 4 additions and 12 deletions
|
|
@ -18,11 +18,11 @@ PyTorch version of [Stable Baselines](https://github.com/hill-a/stable-baselines
|
||||||
## Roadmap
|
## Roadmap
|
||||||
|
|
||||||
TODO:
|
TODO:
|
||||||
- save/load
|
|
||||||
- better predict
|
- better predict
|
||||||
- complete logger
|
- complete logger
|
||||||
- Refactor: buffer with numpy array instead of pytorch
|
- Refactor: buffer with numpy array instead of pytorch
|
||||||
- Refactor: remove duplicated code for evaluation
|
- Refactor: remove duplicated code for evaluation
|
||||||
|
- double check the shape of log prob
|
||||||
|
|
||||||
- plotting? -> zoo
|
- plotting? -> zoo
|
||||||
|
|
||||||
|
|
@ -30,6 +30,7 @@ Later:
|
||||||
- get_parameters / set_parameters
|
- get_parameters / set_parameters
|
||||||
- SDE: use [affine transform](https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/Affine)
|
- SDE: use [affine transform](https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/Affine)
|
||||||
to scale the noise after a tanh transform?
|
to scale the noise after a tanh transform?
|
||||||
|
- Use MultivariateNormal with full covariance matrix?
|
||||||
- CNN policies + normalization
|
- CNN policies + normalization
|
||||||
- tensorboard support
|
- tensorboard support
|
||||||
- DQN
|
- DQN
|
||||||
|
|
|
||||||
|
|
@ -17,15 +17,6 @@ class Distribution(object):
|
||||||
"""
|
"""
|
||||||
raise NotImplementedError
|
raise NotImplementedError
|
||||||
|
|
||||||
# def kl_div(self, other):
|
|
||||||
# """
|
|
||||||
# Calculates the Kullback-Leibler divergence from the given probabilty distribution
|
|
||||||
#
|
|
||||||
# :param other: ([float]) the distribution to compare with
|
|
||||||
# :return: (float) the KL divergence of the two distributions
|
|
||||||
# """
|
|
||||||
# raise NotImplementedError
|
|
||||||
|
|
||||||
def entropy(self):
|
def entropy(self):
|
||||||
"""
|
"""
|
||||||
Returns shannon's entropy of the probability
|
Returns shannon's entropy of the probability
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue