v0.0.1: DiverseRL private -> public change!

DiverseRL is now opened to public!

After long time of developing, I believe my little project can be finally presented.

Currently, DiverseRL supports the following RL algorithms.

• DQN(+DDQN, Dueling DQN, NoisyNet)
• DDPG
• TD3
• SAC
• PPO
• Classic RL algorithms
  • Dyna-Q
  • Q-learning
  • SARSA
  • Monte-carlo model-free control

With features of

• Logging (Wandb, Tensorboard)
• Configuration setting by single yaml file

What's Changed

• Classic rl by @moripiri in #2
• Pre commit/typing to main by @moripiri in #3
• Algos/model free to main by @moripiri in #10
• Feature/log save by @moripiri in #14
• Drop: enhance/multiprocessing by @moripiri in #15
• Enhance/atari env by @moripiri in #16
• Feature/yaml log by @moripiri in #18
• algo/rainbow-dqn by @moripiri in #19
• Enhance/benchmark by @moripiri in #21
• Enhance/ppo done by @moripiri in #22

New Contributors

• @moripiri made their first contribution in #2

Full Changelog: https://github.com/moripiri/DiverseRL/commits/v0.0.1