mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-18 09:54:10 +00:00
Replace "nature" with "Nature" (magazine) to reduce confusion (#965)
* Replace "nature" with "Nature" (magazine) to reduce confusion * Replace "nature" with "Nature" (magazine) to reduce confusion * Update changelog Co-authored-by: mel <callmesolis@gmail.com>
This commit is contained in:
parent
38706f12f3
commit
a18b91e01a
5 changed files with 30 additions and 4 deletions
|
|
@ -141,7 +141,7 @@ DQN
|
||||||
^^^
|
^^^
|
||||||
|
|
||||||
Only the vanilla DQN is implemented right now but extensions will follow.
|
Only the vanilla DQN is implemented right now but extensions will follow.
|
||||||
Default hyperparameters are taken from the nature paper, except for the optimizer and learning rate that were taken from Stable Baselines defaults.
|
Default hyperparameters are taken from the Nature paper, except for the optimizer and learning rate that were taken from Stable Baselines defaults.
|
||||||
|
|
||||||
DDPG
|
DDPG
|
||||||
^^^^
|
^^^^
|
||||||
|
|
|
||||||
|
|
@ -3,6 +3,31 @@
|
||||||
Changelog
|
Changelog
|
||||||
==========
|
==========
|
||||||
|
|
||||||
|
Release 1.6.1a0 (WIP)
|
||||||
|
---------------------------
|
||||||
|
|
||||||
|
Breaking Changes:
|
||||||
|
^^^^^^^^^^^^^^^^^
|
||||||
|
|
||||||
|
New Features:
|
||||||
|
^^^^^^^^^^^^^
|
||||||
|
|
||||||
|
SB3-Contrib
|
||||||
|
^^^^^^^^^^^
|
||||||
|
|
||||||
|
Bug Fixes:
|
||||||
|
^^^^^^^^^^
|
||||||
|
|
||||||
|
Deprecations:
|
||||||
|
^^^^^^^^^^^^^
|
||||||
|
|
||||||
|
Others:
|
||||||
|
^^^^^^^
|
||||||
|
|
||||||
|
Documentation:
|
||||||
|
^^^^^^^^^^^^^^
|
||||||
|
- Fix typo in docstring "nature" -> "Nature" (@Melanol)
|
||||||
|
|
||||||
|
|
||||||
Release 1.6.0 (2022-07-11)
|
Release 1.6.0 (2022-07-11)
|
||||||
---------------------------
|
---------------------------
|
||||||
|
|
@ -986,3 +1011,4 @@ And all the contributors:
|
||||||
@eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler @IperGiove @ScheiklP
|
@eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler @IperGiove @ScheiklP
|
||||||
@simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola @buoyancy99 @caburu @xy9485
|
@simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola @buoyancy99 @caburu @xy9485
|
||||||
@Gregwar @ycheng517 @quantitative-technologies @bcollazo @git-thor @TibiGG @cool-RR @MWeltevrede
|
@Gregwar @ycheng517 @quantitative-technologies @bcollazo @git-thor @TibiGG @cool-RR @MWeltevrede
|
||||||
|
@Melanol
|
||||||
|
|
|
||||||
|
|
@ -50,7 +50,7 @@ class FlattenExtractor(BaseFeaturesExtractor):
|
||||||
|
|
||||||
class NatureCNN(BaseFeaturesExtractor):
|
class NatureCNN(BaseFeaturesExtractor):
|
||||||
"""
|
"""
|
||||||
CNN from DQN nature paper:
|
CNN from DQN Nature paper:
|
||||||
Mnih, Volodymyr, et al.
|
Mnih, Volodymyr, et al.
|
||||||
"Human-level control through deep reinforcement learning."
|
"Human-level control through deep reinforcement learning."
|
||||||
Nature 518.7540 (2015): 529-533.
|
Nature 518.7540 (2015): 529-533.
|
||||||
|
|
|
||||||
|
|
@ -20,7 +20,7 @@ class DQN(OffPolicyAlgorithm):
|
||||||
Deep Q-Network (DQN)
|
Deep Q-Network (DQN)
|
||||||
|
|
||||||
Paper: https://arxiv.org/abs/1312.5602, https://www.nature.com/articles/nature14236
|
Paper: https://arxiv.org/abs/1312.5602, https://www.nature.com/articles/nature14236
|
||||||
Default hyperparameters are taken from the nature paper,
|
Default hyperparameters are taken from the Nature paper,
|
||||||
except for the optimizer and learning rate that were taken from Stable Baselines defaults.
|
except for the optimizer and learning rate that were taken from Stable Baselines defaults.
|
||||||
|
|
||||||
:param policy: The policy model to use (MlpPolicy, CnnPolicy, ...)
|
:param policy: The policy model to use (MlpPolicy, CnnPolicy, ...)
|
||||||
|
|
|
||||||
|
|
@ -1 +1 @@
|
||||||
1.6.0
|
1.6.1a0
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue