RLCodebase 1.0

1. renamed classes like trainers and agents for easier understanding
2. support dm_control suite with visual observation
3. update environment with max step limit
4. support action repeat and reward delay
5. update installation by fixing dependent library versions (gym, mujoco, .etc)

RLCodebase 0.3

Implement Popular RL Algorithms: A2C, PPO, DQN, DDPG, TD3, SAC
Support Multiple Environments: Procgen, Atari, PyBullet, Mujoco

RLCodebase 0.2

Refactor the repo. Add support of DDPG and TD3.

RLCodebase 0.1

Initial release. A2C and PPO are implemented.