Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / ziyadedher/decuen issues and pull requests

#27 - Create simple API tests to ensure consistency of API

Issue - State: open - Opened by ziyadedher about 5 years ago
Labels: enhancement

#26 - Support importance sampling for off-policy policy gradient methods

Issue - State: open - Opened by ziyadedher about 5 years ago
Labels: enhancement

#25 - Implement generic vanilla policy gradient algorithms

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement, algorithm

#24 - Support multiple actor-learners per agent

Issue - State: open - Opened by ziyadedher about 5 years ago
Labels: enhancement

#23 - Refactor code to prepare for policy gradient methods

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

#22 - Improve memory implementation and introduce memory clearing

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement

#21 - Implement Boltzmann strategy (softmax strategy)

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement, algorithm

#20 - Accept latent variable network as input to DQN critic

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement, algorithm

#19 - Migrate framework infrastructure and algorithm implementations to PyTorch

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement, algorithm

#18 - Migrate to PyTorch

Issue - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement

#17 - Fix PyPI setup and update README.md

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: documentation, enhancement

#16 - Remove default settings values

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement

#15 - Simplify Q-learning approaches and create new abstractions

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement

#14 - Introduce higher-order context management for state and action spaces

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement

#13 - Prepare for PyPI deploy

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: documentation, enhancement

#12 - Create CODE_OF_CONDUCT.md

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: documentation, enhancement

#11 - Create and populate GitHub Pages

Issue - State: open - Opened by ziyadedher about 5 years ago
Labels: enhancement

#10 - Populate README.md

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: documentation, enhancement

#9 - Implement vanilla Actor-Critic

Issue - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement, algorithm

#8 - Implement REINFORCE

Issue - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement, algorithm

#7 - Populate README.md with relevant information

Issue - State: closed - Opened by ziyadedher about 5 years ago
Labels: enhancement

#6 - Create and populate a GitHub Wiki

Issue - State: open - Opened by ziyadedher about 5 years ago
Labels: enhancement

#5 - Make documentation compatible with Sphinx

Issue - State: open - Opened by ziyadedher about 5 years ago
Labels: documentation, enhancement, good first issue

#4 - Implement double deep Q-learning

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

#3 - Final merge from master

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

#2 - Introduce Python GitHub action workflow

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: documentation, enhancement

#1 - Create issue templates

Pull Request - State: closed - Opened by ziyadedher about 5 years ago
Labels: documentation