optimizer = optim.Adam(params=policy_net.parameters(), lr=lr)
# Training Loop
episode_durations = []
for episode in range(num_episodes):
em.reset()
state = em.get_state()
for timestep in count():
action = agent.select_action(state, policy_net)
reward = em.take_action(action)
next_state = em.get_state()
memory.push(Experience(state, action, next_state, reward))
state = next_state
if memory.can_provide_sample(batch_size):
experiences = memory.sample(batch_size)
states, actions, rewards, next_states = extract_tensors(
experiences)
current_q_values = QValues.get_current(policy_net, states, actions)
next_q_values = QValues.get_next(target_net, next_states)
target_q_values = (next_q_values * gamma) + rewards
loss = F.mse_loss(current_q_values, target_q_values.unsqueeze(1))
optimizer.zero_grad()
loss.backward()
optimizer.step()
if em.done:
episode_durations.append(timestep)
plotter.plot(episode_durations, 100)