pockerman/py_cube_ai issues and pull requests

#147 - Fix github actions

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

#146 - 145 control diff drive robot q learn

Pull Request - State: closed - Opened by pockerman about 1 year ago - 1 comment
Labels: enhancement

#145 - Control a differential drive robot with Q-learning

Issue - State: open - Opened by pockerman over 1 year ago
Labels: example

#144 - Update examples list

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, example, v0.0.9-alpha, API-V1

#143 - Update example

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#142 - Add REINFORCE C++

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#141 - Refactor RL examples

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, example, v0.0.9-alpha, API-V1

#140 - Add new example

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#139 - Add SARSA on CliffWalk env C++

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#138 - Refactor to API V1

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#137 - Webot support

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: enhancement, example, v0.0.9-alpha

#136 - Add new C++ example documentation

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#135 - Update example documentation

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#134 - Update API

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#133 - Update documentation

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, v0.0.9-alpha, API-V1

#132 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, example, v0.0.9-alpha, API-V1

#131 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, example, v0.0.9-alpha, API-V1

#130 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, example, v0.0.9-alpha, API-V1

#129 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, enhancement, v0.0.9-alpha, API-V1

#128 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#127 - Update implementation

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, v0.0.9-alpha, API-V1

#126 - Webot support

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#125 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#124 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#123 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, v0.0.9-alpha, API-V1

#122 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#121 - Update README

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#120 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#119 - Update to API V1

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: enhancement, example, v0.0.9-alpha, API-V1

#118 - Webot support

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, v0.0.9-alpha, API-V1

#117 - Webot support

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha

#116 - Document Webot support

Issue - State: open - Opened by pockerman almost 3 years ago
Labels: documentation, v0.0.9-alpha

#115 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, enhancement, example, v0.0.9-alpha, API-V1

#114 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, v0.0.9-alpha, API-V1

#113 - Gamma should be incorporated in the environment so that we allow variable discounts

Issue - State: open - Opened by pockerman almost 3 years ago
Labels: enhancement, v0.0.9-alpha, API-V1

#112 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: documentation, test, v0.0.9-alpha

#111 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: bug, v0.0.9-alpha

#110 - #98 Fix workflow

Pull Request - State: closed - Opened by pockerman almost 3 years ago - 1 comment
Labels: bug, v0.0.9-alpha

#109 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, enhancement, example, v0.0.9-alpha, API-V1

#108 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, enhancement, example, v0.0.9-alpha, API-V1

#107 - ```SummaryWriter``` incorporation

Issue - State: open - Opened by pockerman almost 3 years ago

#106 - Refactor to v1 api

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, v0.0.9-alpha, API-V1

#105 - #95 Update documentation

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, v0.0.9-alpha

#104 - Wrappers for step and reset function

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, v0.0.9-alpha, API-V1

#103 - Add test coverage utility

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, test, v0.0.9-alpha

#102 - Update docstrings

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, v0.0.9-alpha

#101 - Add sphinx documentaion

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, v0.0.8-alpha

#100 - Migrate to API V1

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: v0.0.8-alpha

#99 - Actor critic algos

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, example, v0.0.8-alpha

#98 - API V1

Issue - State: open - Opened by pockerman almost 3 years ago
Labels: documentation, v0.0.8-alpha, v0.0.9-alpha, API-V1

#97 - Add Roadmap for versions

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation

#96 - Actor critic algos and API updates

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation, enhancement, example, v0.0.8-alpha

#95 - Documentation generation

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: documentation

#94 - A2C example on CartPole

Issue - State: open - Opened by pockerman almost 3 years ago
Labels: example, v0.0.8-alpha, v0.0.9-alpha

#93 - Add optimization module

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, v0.0.8-alpha

#92 - #71 Refactor Webot environment wrapper

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, example, v0.0.8-alpha

#91 - #89 Add test_suite

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: v0.0.8-alpha, test

#90 - Add test coverage utility

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: test, v0.0.9-alpha

#89 - Add test_suite runner

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: v0.0.8-alpha, test

#88 - Write agent specification document

Issue - State: open - Opened by pockerman almost 3 years ago
Labels: documentation

#87 - #82 API updates and REINFORCE algorithm refactors

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, example, v0.0.7-alpha, test

#86 - rename tiled environment classes

Pull Request - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, v0.0.7-alpha

#85 - Add tests for ReplayBuffer class

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: v0.0.7-alpha, test

#84 - Rename TiledEnvironments to StateAggregation environment

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: bug, v0.0.7-alpha

#83 - Refactor on_episode API to return total episode reward and total number of iterations

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, wontfix, v0.0.8-alpha, v0.0.9-alpha, API-V1

#82 - Refactor REINFORCE algorithm. Introduce REINFORCE for CartPole environment

Issue - State: closed - Opened by pockerman almost 3 years ago
Labels: enhancement, PG, example, v0.0.7-alpha

#81 - DQN target example on Gridworld

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, DQN, example, v0.0.7-alpha

#80 - DQN with target network on Gridworld

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, DQN, example, v0.0.7-alpha

#79 - Markov Decision Process example

Issue - State: open - Opened by pockerman about 3 years ago
Labels: example, v0.0.7-alpha

#78 - #68 Finish dqn example on Gridworld

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: bug, example, v0.0.7-alpha

#77 - DQN with experience replay on Gridworld

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: example, v0.0.7-alpha

#76 - Keras based examples

Issue - State: open - Opened by pockerman about 3 years ago
Labels: example

#75 - Remove old simulator dependency

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: v0.0.8-alpha

#74 - Add links to all the dependencies

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: documentation, v0.0.8-alpha

#73 - Add version module

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: documentation, enhancement, v0.0.7-alpha

#72 - Reward assignement for Webots simulation

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, wontfix, v0.0.7-alpha

#71 - EnvironmentWrapper for Webots should be in the worlds package

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, v0.0.8-alpha

#70 - Finish simple Webots QLearn simulation

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: example, v0.0.8-alpha

#69 - Add Gridworld environment

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, v0.0.7-alpha

#68 - DQN on Gridworld example

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: example, v0.0.7-alpha

#67 - Remove env variable from policies

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, v0.0.7-alpha

#66 - Arm bandit examples

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.7-alpha

#65 - Advertisement placement example

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: example, v0.0.7-alpha

#64 - Arm-bandit example with softmax policy

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: example, v0.0.7-alpha

#63 - Arm-bandit example with epsilon greedy policy

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: example, v0.0.7-alpha

#62 - Fix examples for FrozenLake and CliffWalking for TD algorithms

Issue - State: open - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.9-alpha

#61 - Mountain car example

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.7-alpha

#60 - Add examples from Burton & Sutton book

Issue - State: open - Opened by pockerman about 3 years ago
Labels: example

#59 - Approximate Monte Carlo algorithm

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.7-alpha

#58 - Introduce ```TimeStep``` class for every environment just like DeepMind ACME?

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, question, v0.0.7-alpha

#57 - Maybe introduce trainer for each type of algorithms?

Issue - State: open - Opened by pockerman about 3 years ago
Labels: question

#56 - TiledMountainCar environment

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, v0.0.7-alpha

#55 - #19 Add example

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.6-alpha

#54 - TiledCartPole environment has a bug. We build the same space regardless of the state index

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: bug, v0.0.6-alpha

#53 - Add q learning example on CartPole-v0

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, v0.0.6-alpha

#52 - Fix bounds for tiled cart pole environment

Issue - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement

#51 - Add TD(0) example

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.6-alpha

#50 - Fix bugs

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: bug, example, v0.0.6-alpha

#49 - #36 Add example

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, example, v0.0.5-alpha

#48 - #38 Refactor algorithms

Pull Request - State: closed - Opened by pockerman about 3 years ago
Labels: enhancement, v0.0.5-alpha

GitHub / pockerman/py_cube_ai issues and pull requests