COMA

COMAPolicy

class ding.policy.coma.COMAPolicy(cfg: dict, model: Optional[Union[type, torch.nn.modules.module.Module]] = None, enable_field: Optional[List[str]] = None)

Overview:

Policy class of COMA algorithm. COMA is a multi model reinforcement learning algorithm

Interface:

_init_learn, _data_preprocess_learn, _forward_learn, _reset_learn, _state_dict_learn, _load_state_dict_learn

_init_collect, _forward_collect, _reset_collect, _process_transition, _init_eval, _forward_eval_reset_eval, _get_train_sample, default_model, _monitor_vars_learn

Config:

ID	Symbol	Type	Default Value	Description	Other(Shape)
1	type	str	coma	RL policy register name, refer to registry POLICY_REGISTRY	this arg is optional, a placeholder
2	cuda	bool	False	Whether to use cuda for network	this arg can be diff- erent from modes
3	on_policy	bool	True	Whether the RL algorithm is on-policy or off-policy
	priority	bool	False	Whether use priority(PER)	priority sample, update priority
5	priority_ IS_weight	bool	False	Whether use Importance Sampling Weight to correct biased update.	IS weight
6	learn.update _per_collect	int	1	How many updates(iterations) to train after collector’s one collection. Only valid in serial training	this args can be vary from envs. Bigger val means more off-policy
7	learn.target_ update_theta	float	0.001	Target network update momentum parameter.	between[0,1]
8	learn.discount _factor	float	0.99	Reward’s future discount factor, aka. gamma	may be 1 when sparse reward env
9	learn.td_ lambda	float	0.8	The trade-off factor of td-lambda, which balances 1step td and mc
10	learn.value_ weight	float	1.0	The loss weight of value network	policy network weight is set to 1
11	learn.entropy_ weight	float	0.01	The loss weight of entropy regularization	policy network weight is set to 1

_data_preprocess_learn(data: List[Any]) → dict

Overview:

Preprocess the data to fit the required data format for learning

Arguments:

• data (List[Dict[str, Any]]): the data collected from collect function, the Dict

  in data should contain keys including at least [‘obs’, ‘action’, ‘reward’]

Returns:

• data (Dict[str, Any]): the processed data, including at least

  [‘obs’, ‘action’, ‘reward’, ‘done’, ‘weight’]

_forward_collect(data: dict, eps: float) → dict

Overview:

Collect output according to eps_greedy plugin

Arguments:

• data (dict): Dict type data, including at least [‘obs’].

Returns:

• data (dict): The collected data

_forward_eval(data: dict) → dict

Overview:

Forward function of collect mode, similar to self._forward_collect.

Arguments:

• data (dict): Dict type data, including at least [‘obs’].

Returns:

• output (dict): Dict type data, including at least inferred action according to input obs.

_forward_learn(data: dict) → Dict[str, Any]

Overview:

Forward and backward function of learn mode, acquire the data and calculate the loss andoptimize learner model

Arguments:

• data (Dict[str, Any]): Dict type data, a batch of data for training, values are torch.Tensor or

  np.ndarray or dict/list combinations.

Returns:

• info_dict (Dict[str, Any]): Dict type data, a info dict indicated training result, which will be

  recorded in text log and tensorboard, values are python scalar or a list of scalars.

ArgumentsKeys:

• necessary: obs, action, reward, done, weight

ReturnsKeys:

• necessary: cur_lr, total_loss, policy_loss, value_loss, entropy_loss

  • cur_lr (float): Current learning rate

  • total_loss (float): The calculated loss

  • policy_loss (float): The policy(actor) loss of coma

  • value_loss (float): The value(critic) loss of coma

  • entropy_loss (float): The entropy loss

_get_train_sample(data: collections.deque) → Union[None, List[Any]]

Overview:

Get the train sample from trajectory

Arguments:

• data (deque): The trajectory’s cache

Returns:

• samples (dict): The training samples generated

_init_collect() → None

Overview:

Collect mode init moethod. Called by self.__init__. Init traj and unroll length, collect model. Model has eps_greedy_sample wrapper and hidden state wrapper

_init_eval() → None

Overview:

Evaluate mode init method. Called by self.__init__. Init eval model with argmax strategy and hidden_state plugin.

_init_learn() → None

Overview:

Init the learner model of COMAPolicy

Arguments:

Note

The _init_learn method takes the argument from the self._cfg.learn in the config file

• learning_rate (float): The learning rate fo the optimizer

• gamma (float): The discount factor

• lambda (float): The lambda factor, determining the mix of bootstrapping vs further accumulation of multistep returns at each timestep,

• value_wight(float): The weight of value loss in total loss

• entropy_weight(float): The weight of entropy loss in total loss

• agent_num (int): Since this is a multi-agent algorithm, we need to input the agent num.

• batch_size (int): Need batch size info to init hidden_state plugins

_monitor_vars_learn() → List[str]

Overview:

Return variables’ name if variables are to used in monitor.

Returns:

• vars (List[str]): Variables’ name list.

_process_transition(obs: Any, model_output: dict, timestep: collections.namedtuple) → dict

Overview:

Generate dict type transition data from inputs.

Arguments:

• obs (Any): Env observation

• model_output (dict): Output of collect model, including at least [‘action’, ‘prev_state’]

• timestep (namedtuple): Output after env step, including at least [‘obs’, ‘reward’, ‘done’]

  (here ‘obs’ indicates obs after env step).

Returns:

• transition (dict): Dict type transition data.

default_model() → Tuple[str, List[str]]

Overview:

Return this algorithm default model setting for demonstration.

Returns:

• model_info (Tuple[str, List[str]]): model name and mode import_names

Note

The user can define and use customized network model but must obey the same inferface definition indicated by import_names path. For coma, ding.model.coma.coma