Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / MatthewGerber/rlai issues and pull requests
#62 - 51 tests refactor
Pull Request -
State: closed - Opened by MatthewGerber 3 months ago
#61 - Revisit Swimmer-v4
Issue -
State: closed - Opened by MatthewGerber 9 months ago
- 1 comment
#60 - Gym refactor
Pull Request -
State: closed - Opened by MatthewGerber 9 months ago
#59 - Tick label doesn't show up in state/reward scatter plot for cartpole run.
Issue -
State: open - Opened by MatthewGerber 9 months ago
#58 - Update github workflows to Python 3.11 and pyproject.toml
Issue -
State: closed - Opened by MatthewGerber 9 months ago
- 1 comment
#57 - Rerun continuous mountain car
Issue -
State: closed - Opened by MatthewGerber 9 months ago
#56 - Rerun swimming worm
Issue -
State: closed - Opened by MatthewGerber 9 months ago
#55 - Rerun lunar lander after fixing bug in leg contact
Issue -
State: open - Opened by MatthewGerber 9 months ago
#54 - Revive Jupyter Notebook
Issue -
State: open - Opened by MatthewGerber 9 months ago
#53 - Fix robocode tests
Issue -
State: open - Opened by MatthewGerber 9 months ago
#52 - Add mypy
Issue -
State: closed - Opened by MatthewGerber 9 months ago
#51 - Refactor tests directory layout to match src
Issue -
State: closed - Opened by MatthewGerber 9 months ago
- 1 comment
#50 - Ensure that intercepts are only used where appropriate
Issue -
State: closed - Opened by MatthewGerber 9 months ago
#49 - Use state-dimension segments
Issue -
State: closed - Opened by MatthewGerber 9 months ago
#48 - Remove non-stationary feature scaling
Issue -
State: closed - Opened by MatthewGerber 9 months ago
#47 - Update to Python 3.9
Pull Request -
State: closed - Opened by MatthewGerber about 2 years ago
#46 - Agent refactor
Pull Request -
State: closed - Opened by MatthewGerber over 2 years ago
- 1 comment
#45 - Training pool
Pull Request -
State: closed - Opened by MatthewGerber over 2 years ago
#44 - Train pooling
Pull Request -
State: closed - Opened by MatthewGerber over 2 years ago
#43 - robocode-continuous-test
Pull Request -
State: closed - Opened by MatthewGerber almost 3 years ago
#42 - Continuous mountain car
Pull Request -
State: closed - Opened by MatthewGerber almost 3 years ago
#41 - Robocode continuous
Pull Request -
State: closed - Opened by MatthewGerber almost 3 years ago
#40 - Flake mypy
Pull Request -
State: closed - Opened by MatthewGerber almost 3 years ago
#39 - Try out nan-to-num to use all gradient vectors.
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#38 - Lunar lander fuel level
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#37 - Policy gradient encodings
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#36 - Policy gradient normal and beta distributions
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#35 - Continuous policy gradient
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#34 - Policy gradient
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#33 - v_S refactor
Pull Request -
State: closed - Opened by MatthewGerber about 3 years ago
#32 - Aim move
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#31 - Aim-move
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#30 - Robocode move
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#29 - Robocode movement
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#28 - Get coefficient boxplots to work for actions with varying numbers of features
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#27 - Reward shifting should be delegated to agent
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#26 - Robocode unit test
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#25 - Robocode docs
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#24 - Aiming movement
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#23 - Aiming
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#22 - Robocode firing
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#21 - Robocode
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#20 - Remove epsilon passed to GPI functions
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#19 - Improve pickling
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#18 - Training via Jupyter notebook
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#17 - Model plot
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#16 - Cartpole sgd
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#15 - Reconcile td alpha with function approximation step size (currently ignored)
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#14 - Refactor code to gather up environments, states, and extractors per environment.
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#13 - Update example dependency project to latest rlai version
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#12 - Argument parsing help
Pull Request -
State: closed - Opened by MatthewGerber over 3 years ago
#11 - Refactor entry point to be rlai with sub-commands for train, agent in environment, etc.
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#10 - Chain argument parsers to display help
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
Labels: enhancement
#9 - Increase test coverage
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
#8 - Text/explore passing arguments to scikit-learn SGD model.
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
Labels: enhancement
#7 - Build up examples of practical use/extension
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
Labels: enhancement
#6 - Example/test of state-action interaction feature extractor on command line
Issue -
State: closed - Opened by MatthewGerber over 3 years ago
Labels: enhancement
#4 - Add function approximation
Pull Request -
State: closed - Opened by MatthewGerber almost 4 years ago
#3 - Planning mode
Pull Request -
State: closed - Opened by MatthewGerber almost 4 years ago
#2 - Planning
Pull Request -
State: closed - Opened by MatthewGerber almost 4 years ago
#1 - Migrate DP solver functionality from agent into trainer.py
Issue -
State: closed - Opened by MatthewGerber almost 4 years ago