rlberry-py/rlberry issues and pull requests

#381 - New release, V0.6 (last release before split)

Pull Request - State: closed - Opened by TimotheeMathieu 11 months ago
Labels: ready for review

#380 - Update Tabular RL agents to have epsilon-greedy exploration strategy by default with eps=0.3

Pull Request - State: closed - Opened by riiswa 11 months ago - 1 comment
Labels: ready for review

#380 - Update Tabular RL agents to have epsilon-greedy exploration strategy by default with eps=0.3

Pull Request - State: closed - Opened by riiswa 11 months ago - 1 comment
Labels: ready for review

#379 - Refactorization of the repository

Pull Request - State: closed - Opened by riiswa 11 months ago - 40 comments
Labels: ready for review

#378 - Bump protobuf from 3.20.1 to 4.25.0

Pull Request - State: open - Opened by dependabot[bot] 11 months ago
Labels: dependencies

#377 - [WIP] new feature: runner to launch over multiple virtual environments

Pull Request - State: closed - Opened by TimotheeMathieu 12 months ago - 10 comments
Labels: ready for review

#376 - [WIP] new feature: confidence band around reward curve and proper smoothing

Pull Request - State: closed - Opened by TimotheeMathieu 12 months ago - 17 comments
Labels: ready for review

#375 - [MRG] Added n_simulation in the eval_kwargs

Pull Request - State: closed - Opened by BorisHamadej 12 months ago - 2 comments
Labels: ready for review

#375 - [MRG] Added n_simulation in the eval_kwargs

Pull Request - State: closed - Opened by BorisHamadej 12 months ago - 2 comments
Labels: ready for review

#374 - evaluate_agents do more evaluation than 'n_simulation' param

Issue - State: closed - Opened by JulienT01 12 months ago - 3 comments
Labels: good first issue

#374 - evaluate_agents do more evaluation than 'n_simulation' param

Issue - State: closed - Opened by JulienT01 12 months ago - 3 comments
Labels: good first issue

#373 - Use multiprocessing in eval

Issue - State: open - Opened by TimotheeMathieu 12 months ago

#373 - Use multiprocessing in eval

Issue - State: open - Opened by TimotheeMathieu 12 months ago

#372 - Update ExperimentManager parameters

Issue - State: open - Opened by JulienT01 12 months ago
Labels: good first issue, style

#372 - Update ExperimentManager parameters

Issue - State: open - Opened by JulienT01 12 months ago
Labels: good first issue, style

#371 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: open - Opened by pre-commit-ci[bot] 12 months ago

#370 - Bump protobuf from 3.20.1 to 4.24.4

Pull Request - State: closed - Opened by dependabot[bot] almost 1 year ago - 1 comment
Labels: dependencies

#369 - Upgrade or remove Seaborn

Issue - State: closed - Opened by JulienT01 about 1 year ago

#368 - Bump dm-reverb[tensorflow] from 0.6.1 to 0.13.0

Pull Request - State: open - Opened by dependabot[bot] about 1 year ago
Labels: dependencies

#367 - Update sphinx requirement from <7 to <8

Pull Request - State: open - Opened by dependabot[bot] about 1 year ago
Labels: dependencies

#366 - Upgrade Sphinx version

Issue - State: open - Opened by JulienT01 about 1 year ago
Labels: documentation, dependencies

#366 - Upgrade Sphinx version

Issue - State: open - Opened by JulienT01 about 1 year ago
Labels: documentation, dependencies

#365 - force sphinx version <7

Pull Request - State: closed - Opened by JulienT01 about 1 year ago
Labels: documentation, dependencies, ready for review

#365 - force sphinx version <7

Pull Request - State: closed - Opened by JulienT01 about 1 year ago
Labels: documentation, dependencies, ready for review

#364 - User guide

Pull Request - State: closed - Opened by JulienT01 about 1 year ago - 25 comments
Labels: ready for review

#363 - Bump protobuf from 3.20.1 to 4.24.3

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#363 - Bump protobuf from 3.20.1 to 4.24.3

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#362 - Bump protobuf from 3.20.1 to 4.24.2

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#362 - Bump protobuf from 3.20.1 to 4.24.2

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#361 - Bump protobuf from 3.20.1 to 4.24.1

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#361 - Bump protobuf from 3.20.1 to 4.24.1

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#360 - Bump protobuf from 3.20.1 to 4.24.0

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#360 - Bump protobuf from 3.20.1 to 4.24.0

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#359 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] about 1 year ago

#359 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] about 1 year ago

#358 - Add attributes to A2C

Pull Request - State: open - Opened by riccardodv about 1 year ago - 3 comments

#357 - New Contributors

Pull Request - State: closed - Opened by TimotheeMathieu about 1 year ago
Labels: documentation, ready for review

#357 - New Contributors

Pull Request - State: closed - Opened by TimotheeMathieu about 1 year ago
Labels: documentation, ready for review

#356 - style: uniformize imports

Pull Request - State: open - Opened by AmirAflak about 1 year ago - 1 comment

#355 - Improve docstring and code documentation

Pull Request - State: closed - Opened by JulienT01 about 1 year ago - 6 comments
Labels: documentation, ready for review, Marathon

#354 - Actor Critic Agents are less sample efficient in general (?) since #290

Issue - State: open - Opened by KohlerHECTOR about 1 year ago
Labels: bug, enhancement, question, discussion

#354 - Actor Critic Agents are less sample efficient in general (?) since #290

Issue - State: open - Opened by KohlerHECTOR about 1 year ago
Labels: bug, enhancement, question, discussion

#353 - [WIP] User guide #325

Pull Request - State: closed - Opened by KohlerHECTOR about 1 year ago - 3 comments

#353 - [WIP] User guide #325

Pull Request - State: closed - Opened by KohlerHECTOR about 1 year ago - 3 comments

#352 - Uniformize imports

Issue - State: open - Opened by YannBerthelot about 1 year ago
Labels: good first issue, style

#352 - Uniformize imports

Issue - State: open - Opened by YannBerthelot about 1 year ago
Labels: good first issue, style

#351 - Model factory

Pull Request - State: open - Opened by AleShi94 about 1 year ago - 3 comments
Labels: ready for review, Marathon

#350 - Rename AgentManager to ExperimentManager

Pull Request - State: closed - Opened by RemyDegenne about 1 year ago - 1 comment
Labels: ready for review, Marathon

#350 - Rename AgentManager to ExperimentManager

Pull Request - State: closed - Opened by RemyDegenne about 1 year ago - 1 comment
Labels: ready for review, Marathon

#349 - issue #188

Pull Request - State: closed - Opened by KohlerHECTOR about 1 year ago
Labels: ready for review

#349 - issue #188

Pull Request - State: closed - Opened by KohlerHECTOR about 1 year ago
Labels: ready for review

#348 - Reverse order of lower and upper bounds arguments in bounded UCB/MOSS indices

Pull Request - State: closed - Opened by RemyDegenne about 1 year ago - 1 comment
Labels: enhancement, ready for review

#348 - Reverse order of lower and upper bounds arguments in bounded UCB/MOSS indices

Pull Request - State: closed - Opened by RemyDegenne about 1 year ago - 1 comment
Labels: enhancement, ready for review

#347 - Have all the functions/classes in api.rst

Issue - State: open - Opened by TimotheeMathieu about 1 year ago

#347 - Have all the functions/classes in api.rst

Issue - State: open - Opened by TimotheeMathieu about 1 year ago

#346 - The order of arguments in `makeBoundedUCBIndex` is unintuitive

Issue - State: closed - Opened by RemyDegenne about 1 year ago
Labels: enhancement, Marathon

#346 - The order of arguments in `makeBoundedUCBIndex` is unintuitive

Issue - State: closed - Opened by RemyDegenne about 1 year ago
Labels: enhancement, Marathon

#345 - rename Bernoulli UCB to Bounded UCB

Pull Request - State: closed - Opened by RemyDegenne about 1 year ago
Labels: documentation, ready for review

#345 - rename Bernoulli UCB to Bounded UCB

Pull Request - State: closed - Opened by RemyDegenne about 1 year ago
Labels: documentation, ready for review

#344 - Fix slow multiprocessing

Pull Request - State: open - Opened by riiswa about 1 year ago - 2 comments
Labels: ready for review

#344 - Fix slow multiprocessing

Pull Request - State: open - Opened by riiswa about 1 year ago - 2 comments
Labels: ready for review

#343 - Bernoulli UCB name is misleading in plot_TS_bandit

Issue - State: closed - Opened by RemyDegenne about 1 year ago
Labels: documentation, Marathon

#343 - Bernoulli UCB name is misleading in plot_TS_bandit

Issue - State: closed - Opened by RemyDegenne about 1 year ago
Labels: documentation, Marathon

#342 - Improve docstring and code documentation

Issue - State: open - Opened by JulienT01 about 1 year ago - 1 comment
Labels: documentation, Marathon

#342 - Improve docstring and code documentation

Issue - State: closed - Opened by JulienT01 about 1 year ago - 1 comment
Labels: documentation, Marathon

#341 - Consistent naming

Issue - State: open - Opened by riiswa about 1 year ago

#341 - Consistent naming

Issue - State: open - Opened by riiswa about 1 year ago

#340 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] about 1 year ago

#340 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] about 1 year ago

#339 - Bump protobuf from 3.20.1 to 4.23.4

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#339 - Bump protobuf from 3.20.1 to 4.23.4

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#338 - Bump dm-reverb[tensorflow] from 0.6.1 to 0.12.0

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#338 - Bump dm-reverb[tensorflow] from 0.6.1 to 0.12.0

Pull Request - State: closed - Opened by dependabot[bot] about 1 year ago - 1 comment
Labels: dependencies

#337 - Default value for eval_horizon

Issue - State: open - Opened by TimotheeMathieu about 1 year ago - 7 comments

#337 - Default value for eval_horizon

Issue - State: open - Opened by TimotheeMathieu about 1 year ago - 7 comments

#336 - Changing AgentManager for ExperimentManager

Issue - State: closed - Opened by TimotheeMathieu about 1 year ago - 2 comments
Labels: documentation, good first issue, Marathon

#336 - Changing AgentManager for ExperimentManager

Issue - State: closed - Opened by TimotheeMathieu about 1 year ago - 2 comments
Labels: documentation, good first issue, Marathon

#335 - Upgrade from python3.9 to python3.10

Pull Request - State: closed - Opened by JulienT01 about 1 year ago - 1 comment
Labels: ready for review

#335 - Upgrade from python3.9 to python3.10

Pull Request - State: closed - Opened by JulienT01 about 1 year ago - 1 comment
Labels: ready for review

#334 - Handling **kwargs

Issue - State: open - Opened by TimotheeMathieu about 1 year ago - 3 comments
Labels: documentation, enhancement, style, Marathon

#334 - Handling **kwargs

Issue - State: open - Opened by TimotheeMathieu about 1 year ago - 3 comments
Labels: documentation, enhancement, style, Marathon

#333 - Stopping criterion utility

Issue - State: open - Opened by TimotheeMathieu about 1 year ago - 3 comments
Labels: enhancement, good first issue, Marathon

#333 - Stopping criterion utility

Issue - State: open - Opened by TimotheeMathieu about 1 year ago - 3 comments
Labels: enhancement, good first issue, Marathon

#332 - added probing environments tests on A2C

Pull Request - State: open - Opened by YannBerthelot about 1 year ago - 1 comment
Labels: ready for review, Marathon

#332 - added probing environments tests on A2C

Pull Request - State: open - Opened by YannBerthelot about 1 year ago - 1 comment
Labels: ready for review, Marathon

#329 - Multiprocessing is slow

Issue - State: open - Opened by JulienT01 about 1 year ago - 4 comments
Labels: enhancement, discussion, Marathon

#329 - Multiprocessing is slow

Issue - State: open - Opened by JulienT01 about 1 year ago - 4 comments
Labels: enhancement, discussion, Marathon

#326 - Add Soft Actor-Critic (SAC)

Pull Request - State: closed - Opened by brahimdriss over 1 year ago - 3 comments
Labels: ready for review, Marathon

#326 - Add Soft Actor-Critic (SAC)

Pull Request - State: closed - Opened by brahimdriss over 1 year ago - 3 comments
Labels: ready for review, Marathon

#325 - User guide

Issue - State: open - Opened by TimotheeMathieu over 1 year ago - 3 comments
Labels: documentation, Marathon

#325 - User guide

Issue - State: open - Opened by TimotheeMathieu over 1 year ago - 3 comments
Labels: documentation, Marathon

#322 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] over 1 year ago

#322 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] over 1 year ago

#316 - [WIP] Type hint tests

Pull Request - State: closed - Opened by TimotheeMathieu over 1 year ago - 1 comment

#316 - [WIP] Type hint tests

Pull Request - State: closed - Opened by TimotheeMathieu over 1 year ago - 1 comment

#311 - Impossible to import A2C without optuna in gymnasium branch

Issue - State: open - Opened by YannBerthelot over 1 year ago - 1 comment
Labels: discussion, dependencies, Marathon

#311 - Impossible to import A2C without optuna in gymnasium branch

Issue - State: open - Opened by YannBerthelot over 1 year ago - 1 comment
Labels: discussion, dependencies, Marathon

#302 - PPO x windows = fail

Issue - State: closed - Opened by TimotheeMathieu over 1 year ago

#302 - PPO x windows = fail

Issue - State: closed - Opened by TimotheeMathieu over 1 year ago

#301 - Weird error handling in replay buffer

Issue - State: closed - Opened by TimotheeMathieu over 1 year ago - 1 comment

GitHub / rlberry-py/rlberry issues and pull requests