超级超级小天才的博客

In the previous sections, we try to learn the utility function, or more usually, the action-value functions and greedily select the action with the highest Q-value:π(s)=arg⁡maxa⁡Q(s,a){\pi}(s)=arg ⁡max_a⁡{Q(s,a)}π(s)=arg⁡maxa​⁡Q(s,a)This means that once

Function ApproximationWhile we are learning the Q-functions, but how to represent or record the Q-values? For discrete and finite state space and action space, we can use a big table with size of ∣S∣×∣A∣|S| \times |A|∣S∣×∣A∣ to represent the Q-values for

Model-Free RL MethodIn model-based method, we need firstly model the environment by learning/estimating the transition and reward functions. However, in model-free method, we consider learning the value/utility functions V(s)V(s)V(s) or U(s)U(s)U(s) or ac

Reinforcement LearningFirstly, we assume that all the environments in the following materials are all modeled by Markov decision processes. As we have known, an MDP model can be represented by a tuple (S,A,T,R)(S,A,T,R)(S,A,T,R), the rewards are returned

We now know the most important thing for computing an optimal policy is to compute the value function. But how? (The following contents are all based on infinite horizon problems.) The solution to this problem can be roughly divided into two categories: Va

Markov Decision ProcessOne of the most important problems in decision making is to make sequential decisions, which is also the agent’s utility depends on. At each time step, the agent selects some actions to interact with the environment and make it tran