spinup/algos/pytorch/td3/td3.py [12:182]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class ReplayBuffer:
    """
    A simple FIFO experience replay buffer for TD3 agents.
    """

    def __init__(self, obs_dim, act_dim, size):
        self.obs_buf = np.zeros(core.combined_shape(size, obs_dim), dtype=np.float32)
        self.obs2_buf = np.zeros(core.combined_shape(size, obs_dim), dtype=np.float32)
        self.act_buf = np.zeros(core.combined_shape(size, act_dim), dtype=np.float32)
        self.rew_buf = np.zeros(size, dtype=np.float32)
        self.done_buf = np.zeros(size, dtype=np.float32)
        self.ptr, self.size, self.max_size = 0, 0, size

    def store(self, obs, act, rew, next_obs, done):
        self.obs_buf[self.ptr] = obs
        self.obs2_buf[self.ptr] = next_obs
        self.act_buf[self.ptr] = act
        self.rew_buf[self.ptr] = rew
        self.done_buf[self.ptr] = done
        self.ptr = (self.ptr+1) % self.max_size
        self.size = min(self.size+1, self.max_size)

    def sample_batch(self, batch_size=32):
        idxs = np.random.randint(0, self.size, size=batch_size)
        batch = dict(obs=self.obs_buf[idxs],
                     obs2=self.obs2_buf[idxs],
                     act=self.act_buf[idxs],
                     rew=self.rew_buf[idxs],
                     done=self.done_buf[idxs])
        return {k: torch.as_tensor(v, dtype=torch.float32) for k,v in batch.items()}



def td3(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), seed=0, 
        steps_per_epoch=4000, epochs=100, replay_size=int(1e6), gamma=0.99, 
        polyak=0.995, pi_lr=1e-3, q_lr=1e-3, batch_size=100, start_steps=10000, 
        update_after=1000, update_every=50, act_noise=0.1, target_noise=0.2, 
        noise_clip=0.5, policy_delay=2, num_test_episodes=10, max_ep_len=1000, 
        logger_kwargs=dict(), save_freq=1):
    """
    Twin Delayed Deep Deterministic Policy Gradient (TD3)


    Args:
        env_fn : A function which creates a copy of the environment.
            The environment must satisfy the OpenAI Gym API.

        actor_critic: The constructor method for a PyTorch Module with an ``act`` 
            method, a ``pi`` module, a ``q1`` module, and a ``q2`` module.
            The ``act`` method and ``pi`` module should accept batches of 
            observations as inputs, and ``q1`` and ``q2`` should accept a batch 
            of observations and a batch of actions as inputs. When called, 
            these should return:

            ===========  ================  ======================================
            Call         Output Shape      Description
            ===========  ================  ======================================
            ``act``      (batch, act_dim)  | Numpy array of actions for each 
                                           | observation.
            ``pi``       (batch, act_dim)  | Tensor containing actions from policy
                                           | given observations.
            ``q1``       (batch,)          | Tensor containing one current estimate
                                           | of Q* for the provided observations
                                           | and actions. (Critical: make sure to
                                           | flatten this!)
            ``q2``       (batch,)          | Tensor containing the other current 
                                           | estimate of Q* for the provided observations
                                           | and actions. (Critical: make sure to
                                           | flatten this!)
            ===========  ================  ======================================

        ac_kwargs (dict): Any kwargs appropriate for the ActorCritic object 
            you provided to TD3.

        seed (int): Seed for random number generators.

        steps_per_epoch (int): Number of steps of interaction (state-action pairs) 
            for the agent and the environment in each epoch.

        epochs (int): Number of epochs to run and train agent.

        replay_size (int): Maximum length of replay buffer.

        gamma (float): Discount factor. (Always between 0 and 1.)

        polyak (float): Interpolation factor in polyak averaging for target 
            networks. Target networks are updated towards main networks 
            according to:

            .. math:: \\theta_{\\text{targ}} \\leftarrow 
                \\rho \\theta_{\\text{targ}} + (1-\\rho) \\theta

            where :math:`\\rho` is polyak. (Always between 0 and 1, usually 
            close to 1.)

        pi_lr (float): Learning rate for policy.

        q_lr (float): Learning rate for Q-networks.

        batch_size (int): Minibatch size for SGD.

        start_steps (int): Number of steps for uniform-random action selection,
            before running real policy. Helps exploration.

        update_after (int): Number of env interactions to collect before
            starting to do gradient descent updates. Ensures replay buffer
            is full enough for useful updates.

        update_every (int): Number of env interactions that should elapse
            between gradient descent updates. Note: Regardless of how long 
            you wait between updates, the ratio of env steps to gradient steps 
            is locked to 1.

        act_noise (float): Stddev for Gaussian exploration noise added to 
            policy at training time. (At test time, no noise is added.)

        target_noise (float): Stddev for smoothing noise added to target 
            policy.

        noise_clip (float): Limit for absolute value of target policy 
            smoothing noise.

        policy_delay (int): Policy will only be updated once every 
            policy_delay times for each update of the Q-networks.

        num_test_episodes (int): Number of episodes to test the deterministic
            policy at the end of each epoch.

        max_ep_len (int): Maximum length of trajectory / episode / rollout.

        logger_kwargs (dict): Keyword args for EpochLogger.

        save_freq (int): How often (in terms of gap between epochs) to save
            the current policy and value function.

    """

    logger = EpochLogger(**logger_kwargs)
    logger.save_config(locals())

    torch.manual_seed(seed)
    np.random.seed(seed)

    env, test_env = env_fn(), env_fn()
    obs_dim = env.observation_space.shape
    act_dim = env.action_space.shape[0]

    # Action limit for clamping: critically, assumes all dimensions share the same bound!
    act_limit = env.action_space.high[0]

    # Create actor-critic module and target networks
    ac = actor_critic(env.observation_space, env.action_space, **ac_kwargs)
    ac_targ = deepcopy(ac)

    # Freeze target networks with respect to optimizers (only update via polyak averaging)
    for p in ac_targ.parameters():
        p.requires_grad = False
        
    # List of parameters for both Q-networks (save this for convenience)
    q_params = itertools.chain(ac.q1.parameters(), ac.q2.parameters())

    # Experience buffer
    replay_buffer = ReplayBuffer(obs_dim=obs_dim, act_dim=act_dim, size=replay_size)

    # Count variables (protip: try to get a feel for how different size networks behave!)
    var_counts = tuple(core.count_vars(module) for module in [ac.pi, ac.q1, ac.q2])
    logger.log('\nNumber of parameters: \t pi: %d, \t q1: %d, \t q2: %d\n'%var_counts)

    # Set up function for computing TD3 Q-losses
    def compute_loss_q(data):
        o, a, r, o2, d = data['obs'], data['act'], data['rew'], data['obs2'], data['done']
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



spinup/exercises/pytorch/problem_set_1/exercise1_3.py [27:204]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class ReplayBuffer:
    """
    A simple FIFO experience replay buffer for TD3 agents.
    """

    def __init__(self, obs_dim, act_dim, size):
        self.obs_buf = np.zeros(core.combined_shape(size, obs_dim), dtype=np.float32)
        self.obs2_buf = np.zeros(core.combined_shape(size, obs_dim), dtype=np.float32)
        self.act_buf = np.zeros(core.combined_shape(size, act_dim), dtype=np.float32)
        self.rew_buf = np.zeros(size, dtype=np.float32)
        self.done_buf = np.zeros(size, dtype=np.float32)
        self.ptr, self.size, self.max_size = 0, 0, size

    def store(self, obs, act, rew, next_obs, done):
        self.obs_buf[self.ptr] = obs
        self.obs2_buf[self.ptr] = next_obs
        self.act_buf[self.ptr] = act
        self.rew_buf[self.ptr] = rew
        self.done_buf[self.ptr] = done
        self.ptr = (self.ptr+1) % self.max_size
        self.size = min(self.size+1, self.max_size)

    def sample_batch(self, batch_size=32):
        idxs = np.random.randint(0, self.size, size=batch_size)
        batch = dict(obs=self.obs_buf[idxs],
                     obs2=self.obs2_buf[idxs],
                     act=self.act_buf[idxs],
                     rew=self.rew_buf[idxs],
                     done=self.done_buf[idxs])
        return {k: torch.as_tensor(v, dtype=torch.float32) for k,v in batch.items()}



def td3(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), seed=0, 
        steps_per_epoch=4000, epochs=100, replay_size=int(1e6), gamma=0.99, 
        polyak=0.995, pi_lr=1e-3, q_lr=1e-3, batch_size=100, start_steps=10000, 
        update_after=1000, update_every=50, act_noise=0.1, target_noise=0.2, 
        noise_clip=0.5, policy_delay=2, num_test_episodes=10, max_ep_len=1000, 
        logger_kwargs=dict(), save_freq=1):
    """
    Twin Delayed Deep Deterministic Policy Gradient (TD3)


    Args:
        env_fn : A function which creates a copy of the environment.
            The environment must satisfy the OpenAI Gym API.

        actor_critic: The constructor method for a PyTorch Module with an ``act`` 
            method, a ``pi`` module, a ``q1`` module, and a ``q2`` module.
            The ``act`` method and ``pi`` module should accept batches of 
            observations as inputs, and ``q1`` and ``q2`` should accept a batch 
            of observations and a batch of actions as inputs. When called, 
            these should return:

            ===========  ================  ======================================
            Call         Output Shape      Description
            ===========  ================  ======================================
            ``act``      (batch, act_dim)  | Numpy array of actions for each 
                                           | observation.
            ``pi``       (batch, act_dim)  | Tensor containing actions from policy
                                           | given observations.
            ``q1``       (batch,)          | Tensor containing one current estimate
                                           | of Q* for the provided observations
                                           | and actions. (Critical: make sure to
                                           | flatten this!)
            ``q2``       (batch,)          | Tensor containing the other current 
                                           | estimate of Q* for the provided observations
                                           | and actions. (Critical: make sure to
                                           | flatten this!)
            ===========  ================  ======================================

        ac_kwargs (dict): Any kwargs appropriate for the ActorCritic object 
            you provided to TD3.

        seed (int): Seed for random number generators.

        steps_per_epoch (int): Number of steps of interaction (state-action pairs) 
            for the agent and the environment in each epoch.

        epochs (int): Number of epochs to run and train agent.

        replay_size (int): Maximum length of replay buffer.

        gamma (float): Discount factor. (Always between 0 and 1.)

        polyak (float): Interpolation factor in polyak averaging for target 
            networks. Target networks are updated towards main networks 
            according to:

            .. math:: \\theta_{\\text{targ}} \\leftarrow 
                \\rho \\theta_{\\text{targ}} + (1-\\rho) \\theta

            where :math:`\\rho` is polyak. (Always between 0 and 1, usually 
            close to 1.)

        pi_lr (float): Learning rate for policy.

        q_lr (float): Learning rate for Q-networks.

        batch_size (int): Minibatch size for SGD.

        start_steps (int): Number of steps for uniform-random action selection,
            before running real policy. Helps exploration.

        update_after (int): Number of env interactions to collect before
            starting to do gradient descent updates. Ensures replay buffer
            is full enough for useful updates.

        update_every (int): Number of env interactions that should elapse
            between gradient descent updates. Note: Regardless of how long 
            you wait between updates, the ratio of env steps to gradient steps 
            is locked to 1.

        act_noise (float): Stddev for Gaussian exploration noise added to 
            policy at training time. (At test time, no noise is added.)

        target_noise (float): Stddev for smoothing noise added to target 
            policy.

        noise_clip (float): Limit for absolute value of target policy 
            smoothing noise.

        policy_delay (int): Policy will only be updated once every 
            policy_delay times for each update of the Q-networks.

        num_test_episodes (int): Number of episodes to test the deterministic
            policy at the end of each epoch.

        max_ep_len (int): Maximum length of trajectory / episode / rollout.

        logger_kwargs (dict): Keyword args for EpochLogger.

        save_freq (int): How often (in terms of gap between epochs) to save
            the current policy and value function.

    """

    logger = EpochLogger(**logger_kwargs)
    logger.save_config(locals())

    torch.manual_seed(seed)
    np.random.seed(seed)

    env, test_env = env_fn(), env_fn()
    obs_dim = env.observation_space.shape
    act_dim = env.action_space.shape[0]

    # Action limit for clamping: critically, assumes all dimensions share the same bound!
    act_limit = env.action_space.high[0]

    # Create actor-critic module and target networks
    ac = actor_critic(env.observation_space, env.action_space, **ac_kwargs)
    ac_targ = deepcopy(ac)

    # Freeze target networks with respect to optimizers (only update via polyak averaging)
    for p in ac_targ.parameters():
        p.requires_grad = False
        
    # List of parameters for both Q-networks (save this for convenience)
    q_params = itertools.chain(ac.q1.parameters(), ac.q2.parameters())

    # Experience buffer
    replay_buffer = ReplayBuffer(obs_dim=obs_dim, act_dim=act_dim, size=replay_size)

    # Count variables (protip: try to get a feel for how different size networks behave!)
    var_counts = tuple(core.count_vars(module) for module in [ac.pi, ac.q1, ac.q2])
    logger.log('\nNumber of parameters: \t pi: %d, \t q1: %d, \t q2: %d\n'%var_counts)


    #=========================================================================#
    #                                                                         #
    #           All of your code goes in the space below.                     #
    #                                                                         #
    #=========================================================================#

    # Set up function for computing TD3 Q-losses
    def compute_loss_q(data):
        o, a, r, o2, d = data['obs'], data['act'], data['rew'], data['obs2'], data['done']
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -