train the agent with a new reward

Frontend/main.py

backend/__pycache__/agent.cpython-311.pyc

backend/__pycache__/dqn.cpython-311.pyc

backend/__pycache__/environment.cpython-311.pyc

backend/__pycache__/eventlog.cpython-311.pyc

backend/__pycache__/input.cpython-311.pyc

backend/__pycache__/simplesimmodel.cpython-311.pyc

backend/__pycache__/test.cpython-311.pyc

backend/dqn.py

backend/environment.py

backend/eventlog.py

backend/eventlog_test/optis.csv

backend/main.py

backend/test.py

..._0/events.out.tfevents.1687588176.DESKTOP-N54IHQ9.13300.0

..._0/events.out.tfevents.1687607274.DESKTOP-N54IHQ9.13300.1

..._0/events.out.tfevents.1687614646.DESKTOP-N54IHQ9.17944.0

..._0/events.out.tfevents.1687636161.DESKTOP-N54IHQ9.17944.1

..._0/events.out.tfevents.1687636801.DESKTOP-N54IHQ9.28180.0

..._0/events.out.tfevents.1687645332.DESKTOP-N54IHQ9.28180.1