README.md

reinforcement-learning

强化学习

mdp

• mdp.py
• mdp_value.py

model-based

• mdp.py
• policy_iteration.py
• value_iteration.py

model-free-prediction

• mdp.py
• model_free_policy_evaluation.py

model-free-control

• mdp.py
• model_free_control.py

value-function-approximation

• mdp.py
• evaler.py
• policy.py
• value_function_approximation.py

policy-gradient

• mdp.py
• evaler.py
• policy.py
• policy_gradient.py