caa5ccc42c3d7e0004688a91e9e4a5b42b1a8957,test/test_documentation.py,TestDocumentation,test_readme,#TestDocumentation#,158

Before Change

        agent = Agent.create(
            agent="tensorforce",
            states=dict(type="float", shape=(10,)),
            actions=dict(type="int", num_values=5),
            max_episode_timesteps=100,
            memory=10000,
            update=dict(unit="timesteps", batch_size=64),
            optimizer=dict(type="adam", learning_rate=3e-4),
            policy=dict(network="auto"),
            objective="policy_gradient",
            reward_estimation=dict(horizon=20)
        )

        // Retrieve the latest (observable) environment state
        state = get_current_state()  // (float array of shape [10])

        // Query the agent for its action decision
        action = agent.act(states=state)  // (scalar between 0 and 4)

        // Execute the decision and retrieve the current performance score
        reward = execute_decision(action)  // (any scalar float)

        // Pass feedback about performance (and termination) to the agent
        agent.observe(reward=reward, terminal=False)

After Change

            while not terminal:
                // Episode timestep
                actions = agent.act(states=states)
                states, terminal, reward = environment.execute(actions=actions)
                agent.observe(terminal=terminal, reward=reward)

        agent.close()
        environment.close()

Instances