Decoupled Data-Based Approach for Learning to Control Nonlinear Systems using Model free DDP - D2C-2.0

copyright @ Karthikeya S Parunandi

This repository is an implementation of model free DDP using MuJoCo simulator.

Working systems:

Libraries needed:

Simulator:

Main files:

Name		Name	Last commit message	Last commit date
Latest commit History 34 Commits
__pycache__		__pycache__
backup_previous_ver		backup_previous_ver
experiments		experiments
models		models
params		params
MUJOCO_LOG.TXT		MUJOCO_LOG.TXT
README.md		README.md
acrobot_model_free_DDP.py		acrobot_model_free_DDP.py
cartpole_model_free_ddp.py		cartpole_model_free_ddp.py
double_pendulum_model_free_ddp.py		double_pendulum_model_free_ddp.py
fish_model_free_ddp.py		fish_model_free_ddp.py
half_cheetah_model_free_ddp.py		half_cheetah_model_free_ddp.py
humanoid_model_free_ddp.py		humanoid_model_free_ddp.py
humanoid_standup_model_free_DDP.py		humanoid_standup_model_free_DDP.py
ltv_sys_id.py		ltv_sys_id.py
model_free_DDP.py		model_free_DDP.py
pendulum_model_free_ddp.py		pendulum_model_free_ddp.py
swimmer_6_model_free_ddp.py		swimmer_6_model_free_ddp.py
swimmer_model_free_ddp.py		swimmer_model_free_ddp.py

karthikeyaparunandi/D2C-2.0