├── .gitignore ├── 2IWIL.py ├── IC_GAIL.py ├── README.md ├── conjugate_gradients.py ├── demonstrations ├── Ant-v2_mixture.npy ├── Ant-v2_mixture_conf.npy ├── HalfCheetah-v2_mixture.npy ├── HalfCheetah-v2_mixture_conf.npy ├── Hopper-v2_mixture.npy ├── Hopper-v2_mixture_conf.npy ├── Swimmer-v2_mixture.npy ├── Swimmer-v2_mixture_conf.npy ├── Walker2d-v2_mixture.npy └── Walker2d-v2_mixture_conf.npy ├── loss.py ├── models.py ├── replay_memory.py ├── running_state.py ├── trpo.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | model/ 2 | log/ 3 | execute.sh 4 | output/ 5 | __pycache__/ 6 | -------------------------------------------------------------------------------- /2IWIL.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/2IWIL.py -------------------------------------------------------------------------------- /IC_GAIL.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/IC_GAIL.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/README.md -------------------------------------------------------------------------------- /conjugate_gradients.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/conjugate_gradients.py -------------------------------------------------------------------------------- /demonstrations/Ant-v2_mixture.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Ant-v2_mixture.npy -------------------------------------------------------------------------------- /demonstrations/Ant-v2_mixture_conf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Ant-v2_mixture_conf.npy -------------------------------------------------------------------------------- /demonstrations/HalfCheetah-v2_mixture.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/HalfCheetah-v2_mixture.npy -------------------------------------------------------------------------------- /demonstrations/HalfCheetah-v2_mixture_conf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/HalfCheetah-v2_mixture_conf.npy -------------------------------------------------------------------------------- /demonstrations/Hopper-v2_mixture.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Hopper-v2_mixture.npy -------------------------------------------------------------------------------- /demonstrations/Hopper-v2_mixture_conf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Hopper-v2_mixture_conf.npy -------------------------------------------------------------------------------- /demonstrations/Swimmer-v2_mixture.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Swimmer-v2_mixture.npy -------------------------------------------------------------------------------- /demonstrations/Swimmer-v2_mixture_conf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Swimmer-v2_mixture_conf.npy -------------------------------------------------------------------------------- /demonstrations/Walker2d-v2_mixture.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Walker2d-v2_mixture.npy -------------------------------------------------------------------------------- /demonstrations/Walker2d-v2_mixture_conf.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/demonstrations/Walker2d-v2_mixture_conf.npy -------------------------------------------------------------------------------- /loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/loss.py -------------------------------------------------------------------------------- /models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/models.py -------------------------------------------------------------------------------- /replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/replay_memory.py -------------------------------------------------------------------------------- /running_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/running_state.py -------------------------------------------------------------------------------- /trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/trpo.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kristery/Imitation-Learning-from-Imperfect-Demonstration/HEAD/utils.py --------------------------------------------------------------------------------