spinup/algos/pytorch/ddpg/ddpg.py [219:280]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        with torch.no_grad():
            for p, p_targ in zip(ac.parameters(), ac_targ.parameters()):
                # NB: We use an in-place operations "mul_", "add_" to update target
                # params, as opposed to "mul" and "add", which would make new tensors.
                p_targ.data.mul_(polyak)
                p_targ.data.add_((1 - polyak) * p.data)

    def get_action(o, noise_scale):
        a = ac.act(torch.as_tensor(o, dtype=torch.float32))
        a += noise_scale * np.random.randn(act_dim)
        return np.clip(a, -act_limit, act_limit)

    def test_agent():
        for j in range(num_test_episodes):
            o, d, ep_ret, ep_len = test_env.reset(), False, 0, 0
            while not(d or (ep_len == max_ep_len)):
                # Take deterministic actions at test time (noise_scale=0)
                o, r, d, _ = test_env.step(get_action(o, 0))
                ep_ret += r
                ep_len += 1
            logger.store(TestEpRet=ep_ret, TestEpLen=ep_len)

    # Prepare for interaction with environment
    total_steps = steps_per_epoch * epochs
    start_time = time.time()
    o, ep_ret, ep_len = env.reset(), 0, 0

    # Main loop: collect experience in env and update/log each epoch
    for t in range(total_steps):
        
        # Until start_steps have elapsed, randomly sample actions
        # from a uniform distribution for better exploration. Afterwards, 
        # use the learned policy (with some noise, via act_noise). 
        if t > start_steps:
            a = get_action(o, act_noise)
        else:
            a = env.action_space.sample()

        # Step the env
        o2, r, d, _ = env.step(a)
        ep_ret += r
        ep_len += 1

        # Ignore the "done" signal if it comes from hitting the time
        # horizon (that is, when it's an artificial terminal signal
        # that isn't based on the agent's state)
        d = False if ep_len==max_ep_len else d

        # Store experience to replay buffer
        replay_buffer.store(o, a, r, o2, d)

        # Super critical, easy to overlook step: make sure to update 
        # most recent observation!
        o = o2

        # End of trajectory handling
        if d or (ep_len == max_ep_len):
            logger.store(EpRet=ep_ret, EpLen=ep_len)
            o, ep_ret, ep_len = env.reset(), 0, 0

        # Update handling
        if t >= update_after and t % update_every == 0:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



spinup/algos/pytorch/td3/td3.py [259:320]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            with torch.no_grad():
                for p, p_targ in zip(ac.parameters(), ac_targ.parameters()):
                    # NB: We use an in-place operations "mul_", "add_" to update target
                    # params, as opposed to "mul" and "add", which would make new tensors.
                    p_targ.data.mul_(polyak)
                    p_targ.data.add_((1 - polyak) * p.data)

    def get_action(o, noise_scale):
        a = ac.act(torch.as_tensor(o, dtype=torch.float32))
        a += noise_scale * np.random.randn(act_dim)
        return np.clip(a, -act_limit, act_limit)

    def test_agent():
        for j in range(num_test_episodes):
            o, d, ep_ret, ep_len = test_env.reset(), False, 0, 0
            while not(d or (ep_len == max_ep_len)):
                # Take deterministic actions at test time (noise_scale=0)
                o, r, d, _ = test_env.step(get_action(o, 0))
                ep_ret += r
                ep_len += 1
            logger.store(TestEpRet=ep_ret, TestEpLen=ep_len)

    # Prepare for interaction with environment
    total_steps = steps_per_epoch * epochs
    start_time = time.time()
    o, ep_ret, ep_len = env.reset(), 0, 0

    # Main loop: collect experience in env and update/log each epoch
    for t in range(total_steps):
        
        # Until start_steps have elapsed, randomly sample actions
        # from a uniform distribution for better exploration. Afterwards, 
        # use the learned policy (with some noise, via act_noise). 
        if t > start_steps:
            a = get_action(o, act_noise)
        else:
            a = env.action_space.sample()

        # Step the env
        o2, r, d, _ = env.step(a)
        ep_ret += r
        ep_len += 1

        # Ignore the "done" signal if it comes from hitting the time
        # horizon (that is, when it's an artificial terminal signal
        # that isn't based on the agent's state)
        d = False if ep_len==max_ep_len else d

        # Store experience to replay buffer
        replay_buffer.store(o, a, r, o2, d)

        # Super critical, easy to overlook step: make sure to update 
        # most recent observation!
        o = o2

        # End of trajectory handling
        if d or (ep_len == max_ep_len):
            logger.store(EpRet=ep_ret, EpLen=ep_len)
            o, ep_ret, ep_len = env.reset(), 0, 0

        # Update handling
        if t >= update_after and t % update_every == 0:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -