Create SOC Agent
this agent provides a on policy (deterministic policy) method where the update of the policy is given by the gradient of the soc objective function which is provided. The mc estimator of the gradient is given and depends on the path and on the derivatives of the policy.
- create soc agent module
- create soc algorithm module
- create script to run the soc algorithm for the sde environment
- create script visualize the soc algorithm results for the sde environment