learnables/cherry issues and pull requests

#46 - Fixed the wrong linear scaling in `ActionSpaceScaler`

Pull Request - State: closed - Opened by gwwo almost 2 years ago - 1 comment

#45 - Questionable Code in `ActionSpaceScaler`

Issue - State: closed - Opened by gwwo almost 2 years ago - 2 comments

#44 - Bump mkdocs from 1.0.4 to 1.2.3

Pull Request - State: open - Opened by dependabot[bot] over 2 years ago
Labels: dependencies

#43 - pip install cherry-rl error

Issue - State: closed - Opened by StewartTsai over 2 years ago - 1 comment

#42 - encoding problem fixed

Pull Request - State: closed - Opened by 3DAlgoLab over 2 years ago - 2 comments

#41 - Using cherry optimizer with learning rate schedulers

Issue - State: closed - Opened by arijitthegame almost 3 years ago - 2 comments

#40 - Bring Fixes from Jumping

Pull Request - State: closed - Opened by seba-1511 over 3 years ago

#39 - v0.2.0: Policy, Value Functions, and more Algorithms

Pull Request - State: closed - Opened by seba-1511 over 3 years ago

#38 - Various fixes to recent PyTorch and Gym updates.

Pull Request - State: closed - Opened by seba-1511 almost 4 years ago

#37 - PPO dual clip

Pull Request - State: open - Opened by MehdiZouitine almost 4 years ago

#36 - Error using cherry and multiprocessing

Issue - State: closed - Opened by nilslacroix about 4 years ago - 4 comments

#35 - Fix variance update in state/reward normalizers.

Pull Request - State: closed - Opened by seba-1511 over 4 years ago

#34 - Fix StateNormalizer and RewardNormalizer wrappers.

Pull Request - State: closed - Opened by seba-1511 over 4 years ago

#33 - StateNormalizer returning None

Issue - State: closed - Opened by Coolnesss over 4 years ago - 1 comment

#32 - More intuitive CUDA support for Runner?

Issue - State: closed - Opened by Kostis-S-Z over 4 years ago - 3 comments
Labels: beginner

#31 - Version bump and add torch 1.5 to travis.

Pull Request - State: closed - Opened by seba-1511 over 4 years ago

#30 - Fix PyTorch 1.5.0 incompatibility in replay buffer

Pull Request - State: closed - Opened by ManifoldFR over 4 years ago - 1 comment

#29 - fix bug in torch_wrapper when use GPU

Pull Request - State: closed - Opened by walkacross over 4 years ago - 1 comment

#28 - Fix action and state sizes for num vec envs = 1

Pull Request - State: closed - Opened by seba-1511 over 4 years ago

#27 - Vec discount fix

Pull Request - State: closed - Opened by galatolofederico over 4 years ago - 1 comment

#26 - New A2C example with entropy

Pull Request - State: open - Opened by galatolofederico over 4 years ago - 4 comments

#25 - Wrong action_size and observation shape in Torch Wrapper

Pull Request - State: closed - Opened by galatolofederico over 4 years ago - 2 comments

#24 - Add CHANGELOG.md and update testing tasks.

Pull Request - State: closed - Opened by seba-1511 over 4 years ago

#23 - Fix for issue #22

Pull Request - State: closed - Opened by ngoby over 4 years ago - 3 comments

#22 - AttributeError 'numpy.int64' object has no attribute 'device' when running tabular/q_learning.py example

Issue - State: closed - Opened by ngoby over 4 years ago - 1 comment

#21 - Running episodes in parallel

Issue - State: closed - Opened by Coolnesss almost 5 years ago - 4 comments

#20 - Support torch 1.3.0

Pull Request - State: closed - Opened by seba-1511 about 5 years ago

#19 - Fix Logger wrapper for SyncVecEnv.

Pull Request - State: closed - Opened by seba-1511 about 5 years ago

#18 - Logger wrapper now uses python logging facilities.

Pull Request - State: closed - Opened by ian-bunner over 5 years ago - 1 comment

#17 - Fix onehot

Pull Request - State: closed - Opened by ian-bunner over 5 years ago