Changelog

0.13 (2023-09-19)

• Creating a ppo agent training on continuous action space

• Adding two environments: Pendulum-v1 and MountainCarContinuous-v0

• Creating two new environments: PointMass1D-v0 and PointMass2D-v0

• Creating test cases: test_gae.py, test_returns_and_advantages.py, test_normalizer.py, test_random_utils.py , test_reward_scaler.py

0.11 (2023-07-03)

• Creating a ppo agent training on discrete action space

• Adding one environment: CartPole-v1

0.1 (2023-07-01)

• Initial release to PyPI