Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Sep 11, 2025

• Merge pull request #6 from AspadaX/sac

  Show description for 0476665
  AspadaX

  authored
  0476665View commit details

  Copy full SHA for 0476665

  Browse repository at this point

• Remove hardcoded AC algorithm execution and add user input prompt

  AspadaX

  committed
  b8f9ff4View commit details

  Copy full SHA for b8f9ff4

  Browse repository at this point

Commits on Sep 10, 2025

• remove unused imports

  

  xinyubao

  committed
  054e1d2View commit details

  Copy full SHA for 054e1d2

  Browse repository at this point

• Remove Python implementation and refactor Rust actor-critic

  Show description for 45edb40
  

  xinyubao

  committed
  45edb40View commit details

  Copy full SHA for 45edb40

  Browse repository at this point

Commits on Sep 9, 2025

• updating Actor-Critic algorithm

  AspadaX

  committed
  d2d0410View commit details

  Copy full SHA for d2d0410

  Browse repository at this point

Commits on Sep 8, 2025

• updated the ac, but it will need a rewrite

  

  xinyubao

  committed
  d3d0d8bView commit details

  Copy full SHA for d3d0d8b

  Browse repository at this point

Commits on Sep 6, 2025

• Add replay buffer with max capacity and fix DQN training loop

  Show description for 48b8aeb
  

  xinyubao

  committed
  48b8aebView commit details

  Copy full SHA for 48b8aeb

  Browse repository at this point

• Refactor PPO data handling and fix DQN memory usage

  Show description for cfea396
  

  xinyubao

  committed
  cfea396View commit details

  Copy full SHA for cfea396

  Browse repository at this point

Commits on Sep 2, 2025

• Refactor to share common data structures and replay buffer

  

  xinyubao

  committed
  db20c74View commit details

  Copy full SHA for db20c74

  Browse repository at this point

• Rename `action_prob` to `action_probability` and add `from_step_result` constructor

  AspadaX

  committed
  f39e537View commit details

  Copy full SHA for f39e537

  Browse repository at this point

• Refactor module structure and add SAC skeleton

  Show description for 1fa5b05
  AspadaX

  committed
  1fa5b05View commit details

  Copy full SHA for 1fa5b05

  Browse repository at this point

Commits on Sep 1, 2025

• Update main.rs

  AspadaX

  authored
  85226e0View commit details

  Copy full SHA for 85226e0

  Browse repository at this point

• Rename a2c module to ac and update references

  AspadaX

  committed
  a22dc92View commit details

  Copy full SHA for a22dc92

  Browse repository at this point

• Update README.md

  AspadaX

  authored
  c40cfdeView commit details

  Copy full SHA for c40cfde

  Browse repository at this point

• Merge pull request #5 from AspadaX/a2c

  Show description for 4a2929c
  AspadaX

  authored
  4a2929cView commit details

  Copy full SHA for 4a2929c

  Browse repository at this point

• Add A2C implementation and refactor shared Relu layers

  Show description for 728bb0b
  AspadaX

  committed
  728bb0bView commit details

  Copy full SHA for 728bb0b

  Browse repository at this point

Commits on Aug 30, 2025

• Refactor A2C implementation and fix TD target calculation

  Show description for 179ad74
  

  xinyubao

  committed
  179ad74View commit details

  Copy full SHA for 179ad74

  Browse repository at this point

Commits on Aug 29, 2025

• added a2c to main

  AspadaX

  committed
  d342490View commit details

  Copy full SHA for d342490

  Browse repository at this point

• finished training loop of a2c

  AspadaX

  committed
  28c9954View commit details

  Copy full SHA for 28c9954

  Browse repository at this point

Commits on Aug 28, 2025

• Implement TD target computation for A2C training loop

  

  xinyubao

  committed
  9152959View commit details

  Copy full SHA for 9152959

  Browse repository at this point

• Add gym-rs dependency and update environment interaction logic

  

  xinyubao

  committed
  b4c06a3View commit details

  Copy full SHA for b4c06a3

  Browse repository at this point

• updates

  AspadaX

  committed
  b31ff8aView commit details

  Copy full SHA for b31ff8a

  Browse repository at this point

Commits on Aug 27, 2025

• updated readme

  AspadaX

  committed
  c75b9c9View commit details

  Copy full SHA for c75b9c9

  Browse repository at this point

• Refactor action sampling into shared utility and add A2C training loop

  AspadaX

  committed
  8050f22View commit details

  Copy full SHA for 8050f22

  Browse repository at this point

Commits on Aug 26, 2025

• Remove unused dependencies and add A2C module

  AspadaX

  committed
  4915298View commit details

  Copy full SHA for 4915298

  Browse repository at this point

Commits on Aug 25, 2025

• Add usage instructions to README

  AspadaX

  committed
  48e0b72View commit details

  Copy full SHA for 48e0b72

  Browse repository at this point

• Merge pull request #4 from AspadaX/dqn

  Show description for e2965e5
  AspadaX

  authored
  e2965e5View commit details

  Copy full SHA for e2965e5

  Browse repository at this point

• Update README with DQN completion and project progress

  AspadaX

  committed
  b59cfdaView commit details

  Copy full SHA for b59cfda

  Browse repository at this point

• Remove hardcoded DQN session and add algorithm selection prompt

  AspadaX

  committed
  36cf7b8View commit details

  Copy full SHA for 36cf7b8

  Browse repository at this point

Commits on Aug 24, 2025

• Fix argmax dimension and target network output calculation in DQN

  

  xinyubao

  committed
  8c1ddd6View commit details

  Copy full SHA for 8c1ddd6

  Browse repository at this point

• added a simple cli to activate different algorithm

  

  xinyubao

  committed
  190494aView commit details

  Copy full SHA for 190494a

  Browse repository at this point

Commits on Aug 22, 2025

• Refactor DQN training loop and implement Huber loss

  Show description for 2717c8e
  AspadaX

  committed
  2717c8eView commit details

  Copy full SHA for 2717c8e

  Browse repository at this point

Commits on Aug 21, 2025

• Add DQN training loop and improve documentation

  Show description for 2901b3d
  AspadaX

  committed
  2901b3dView commit details

  Copy full SHA for 2901b3d

  Browse repository at this point

• Implement DQN forward pass and action sampling, make PPO methods immutable

  AspadaX

  committed
  229be46View commit details

  Copy full SHA for 229be46

  Browse repository at this point

• Implement replay buffer and Q-network for DQN agent

  AspadaX

  committed
  1127588View commit details

  Copy full SHA for 1127588

  Browse repository at this point