Explain the key component of reinforcement learning and demonstrate the application in the contest of financial data using this lab$-$ define rl $-$make decision based on interaction with environment$-$achieve goal$-$components: aeasrp $($refer notes and the lab$)1.$ agent$-$learner $/$ decision maker$-$interact with environment$-$trading algorithm $->$ action $($buy$,$ sell, hold assets$)$ based on market conditions $($environment$)2.$ Environment$-$external system agent interact$-$market price change $($this lab based on FOREX data$)$ based on market conditions, economic indicators$3.$ Action$-$moves that agent can make$-$buy, sell, hold the stock$4.$ State$-$Current situation of environment$-$indicator$-$help agent make decision$5.$ Reward$-$feedback from environment as a result of agents actionS$-$profit $/$ loss$6.$ Policy$-$strategy for agent to take actions$-$ max rewards