10.a] Determine characteristics, applications, and challenges of Reinforcement Learning.
Answer:
Characteristics of Reinforcement Learning:
- Sequential decision making – Consider the Figure 14.3. It can be seen the path from Start to goal is not done in one Step. It is a sequence of decisions that leads to the goal. One wrong move may result in a failure. This is the main characteristic of reinforcement learning.
- Delayed feedback – Often, rewards are not immediate. One must spend many moves to get final success or failure. Feedback in terms of reward is often delayed.
- The agent actions are interdependent as any action affects the subsequent actions. For example, one wrong move of an agent may lead to failure.
- Time related – All actions are associated with time stamps inherently as all actions are ordered as per the timeline inherently.
Applications of Reinforcement Learning:
There are many applications Of RL Some Of the application domains where reinforcement learning
is used are listed below:
- Industrial automation
- Resource management applications to allocate resource
- Traffic light controller to reduce congestion of traffic
- Personalized recommendation systems like news
- Bidding for advertisement
- Customized applications
- Driverless cars
- Along with deep learning games like Chess and GO
- Deep mind applications like to generate programs and images
Challenges of Reinforcement Learning:
- Reward design is a big challenge as in many games, as determining the rewards and its value is a challenge.
- Absence of a model is a challenge – Games like chess have fixed board and rules. But, many games do not have any fixed environment or rules. There is no underlying model as well. so, simulation must be done to gather experience.
- Partial observability Of States – Many states are fully observable. Imagine a scenario in a weather forecasting where the uncertainty or partial observability exists as complete information about the state is simply not available.
- Time consuming operations – More state spaces and possible actions may complicate the scenarios, resulting in more time consumption.
- Complexity – Many games like GO are complicated with much larger board configuration and many possibilities of actions. So, labelled data is simply not available. This adds more complexity to the design of reinforcement algorithms.