Symbol | Meaning |
| States. |
| Actions. |
| Results. |
q | A transition function which gives the probability of moving from one state to another. |
| State, action, and reward at time step t for one trajectory. |
| Reward for taking action at state and moving to the new state . Sometimes the notation is used as well. |
| A reinforcement learning policy, which maps states to actions. is a policy parameterized by . |
| Cumulative reward for a policy. |
| Horizon which is the length of time a reinforcement policy can do actions. |
| Discount factor which discounts future rewards. |
| Step size hyperparameter. |
| Hyper parameter which controls how much random variance or “jitter” is applied to the Natural Evolutionary Strategy populations. |
| Final portfolio value. |
| Quantum Rotation gate. |
| Quantum Displacement gate. |
| Quantum Squeezing gate. |
| Quantum Beamsplitter gate that allows for entanglement between two photons. |
| Quantum Kerr gate. |