Go to the source code of this file.
Namespaces | |
| qtable | |
Functions | |
| def | qtable.rendertrial (maxiter=100) |
Variables | |
| float | qtable.DECAY_RATE = 0.99 |
| qtable.env = DPendulum() | |
| list | qtable.h_rwd = [] |
| float | qtable.LEARNING_RATE = 0.85 |
| int | qtable.NEPISODES = 500 |
| int | qtable.NSTEPS = 50 |
| qtable.NU = env.nu | |
| qtable.NX = env.nx | |
| qtable.Q = np.zeros([env.nx, env.nu]) | |
| float | qtable.Qref = reward + DECAY_RATE * np.max(Q[x2, :]) |
| qtable.RANDOM_SEED = int((time.time() % 10) * 1000) | |
| qtable.reward | |
| float | qtable.rsum = 0.0 |
| qtable.u | |
| qtable.x = env.reset() | |
| qtable.x2 | |