`scml.std.rl`

Submodules

Package Contents

Classes

`ActionManager`	Manges actions of an agent in an RL environment.
`FlexibleActionManager`	An action manager that matches any context.
`StdEnv`	The main Gymnasium class for implementing Reinforcement Learning Agents environments.
`ObservationManager`	Manages the observations of an agent in an RL environment
`FlexibleObservationManager`	An observation manager that can be used with any SCML world.
`RewardFunction`	Represents a reward function.
`DefaultRewardFunction`	The default reward function of SCML

Functions

`model_wrapper`(→ RLModel)	Wraps a stable_baselines3 model as an RL model
`random_action`(→ numpy.ndarray)	Samples a random action from the action space of the
`random_policy`(→ numpy.ndarray)	Ends the negotiation or accepts with a predefined probability or samples a random response.
`greedy_policy`()[, debug])	A simple greedy policy.

Attributes

`DefaultActionManager`	The default action manager
`StdRLAgent`
`RLState`	We assume that RL states are numpy arrays
`RLAction`	We assume that RL actions are numpy arrays
`RLModel`	A policy is a callable that receives a state and returns an action
`DefaultObservationManager`	The default observation manager
`__all__`

class scml.std.rl.ActionManager[source]

Bases: abc.ABC

Manges actions of an agent in an RL environment.

context: scml.oneshot.context.BaseContext

continuous: bool = False

n_suppliers: int

n_consumers: int

n_partners: int

abstract make_space() → gymnasium.Space[source]: Creates the action space

abstract decode(awi: scml.oneshot.awi.OneShotAWI, action: numpy.ndarray) → dict[str, negmas.sao.common.SAOResponse][source]: Decodes an action from an array to a PurchaseOrder and a CounterMessage.

encode(awi: scml.oneshot.awi.OneShotAWI, responses: dict[str, negmas.sao.common.SAOResponse]) → numpy.ndarray[source]: Encodes an action as an array. This is only used for testing so it is optional

class scml.std.rl.FlexibleActionManager[source]

Bases: ActionManager

An action manager that matches any context.

Parameters:

n_prices – Number of distinct prices allowed in the action.
max_quantity – Maximum allowed quantity to offer in any negotiation. The number of quantities is one plus that because zero is allowed to model ending negotiation.
n_partners – Maximum of partners allowed in the action.

Remarks:

This action manager will always generate offers that are within the price and quantity limits given in its parameters. Wen decoding them, it will scale them up so that the maximum corresponds to the actual value in the world it finds itself. For example, if n_prices is 10 and the world has only two prices currently in the price issue, it will use any value less than 5 as the minimum price and any value above 5 as the maximum price. If on the other hand the current price issue has 20 values, then it will scale by multiplying the number given in the encoded action (ranging from 0 to 9) by 19/9 which makes it range from 0 to 19 which is what is expected by the world.
This action manager will adjust offers for different number of partners as follows: - If the true number of partners is larger than n_partners used by this action manager,

it will simply use n_partners of them and always end negotiations with the rest of them.
- If the true number of partners is smaller than n_partners, it will use the first n_partners values in the encoded action and increase the quantities of any counter offers (i.e. ones in which the response is REJECT_OFFER) by the amount missing from the ignored partners in the encoded action up to the maximum quantities allowed by the current negotiation context. For example, if n_partneers is 4 and we have only 2 partners in reality, and the received quantities from partners were [4, 3] while the maximum quantity allowed is 10 and the encoded action was [2, *, 3, *, 2, *, 1, *] (where we ignored prices), then the encoded action will be converted to [(Reject, 5, *), (Accept, 3, *)] where the 3 extra units that were supposed to be offered to the last two partners are moved to the first partner. If the maximum quantity allowed was 4 in that example, the result will be [(Reject, 4, *), (Accept, 3, *)].

capacity_multiplier: int = 1

n_prices: int = 2

max_group_size: int = 2

reduce_space_size: bool = True

extra_checks: bool = False

max_quantity: int

__attrs_post_init__()[source]

make_space() → gymnasium.spaces.MultiDiscrete | gymnasium.spaces.Box[source]: Creates the action space

decode(awi: scml.oneshot.awi.OneShotAWI, action: numpy.ndarray) → dict[str, negmas.sao.common.SAOResponse][source]: Generates offers to all partners from an encoded action. Default is to return the action as it is assuming it is a dict[str, SAOResponse]

encode(awi: scml.oneshot.awi.OneShotAWI, responses: dict[str, negmas.sao.common.SAOResponse]) → numpy.ndarray[source]: Receives offers for all partners and generates the corresponding action. Used mostly for debugging and testing.

scml.std.rl.DefaultActionManager[source]: The default action manager

scml.std.rl.StdRLAgent[source]

scml.std.rl.RLState[source]: We assume that RL states are numpy arrays

scml.std.rl.RLAction[source]: We assume that RL actions are numpy arrays

scml.std.rl.RLModel[source]: A policy is a callable that receives a state and returns an action

scml.std.rl.model_wrapper(model, deterministic: bool = False) → RLModel[source]: Wraps a stable_baselines3 model as an RL model

class scml.std.rl.StdEnv(action_manager: scml.oneshot.rl.action.ActionManager, observation_manager: scml.oneshot.rl.observation.ObservationManager, reward_function: scml.oneshot.rl.reward.RewardFunction = DefaultRewardFunction(), render_mode=None, context: scml.oneshot.context.GeneralContext = FixedPartnerNumbersStdContext(), agent_type: type[scml.std.agent.StdAgent] = StdPlaceholder, agent_params: dict[str, Any] | None = None, extra_checks: bool = True, skip_after_negotiations: bool = True)[source]

Bases: scml.oneshot.rl.env.OneShotEnv

The main Gymnasium class for implementing Reinforcement Learning Agents environments.

The class encapsulates an environment with arbitrary behind-the-scenes dynamics through the step() and reset() functions. An environment can be partially or fully observed by single agents. For multi-agent environments, see PettingZoo.

The main API methods that users of this class need to know are:

step() - Updates an environment with actions returning the next agent observation, the reward for taking that actions, if the environment has terminated or truncated due to the latest action and information from the environment about the step, i.e. metrics, debug info.
reset() - Resets the environment to an initial state, required before calling step. Returns the first agent observation for an episode and information, i.e. metrics, debug info.
render() - Renders the environments to help visualise what the agent see, examples modes are “human”, “rgb_array”, “ansi” for text.
close() - Closes the environment, important when external software is used, i.e. pygame for rendering, databases

Environments have additional attributes for users to understand the implementation

action_space - The Space object corresponding to valid actions, all valid actions should be contained within the space.
observation_space - The Space object corresponding to valid observations, all valid observations should be contained within the space.
reward_range - A tuple corresponding to the minimum and maximum possible rewards for an agent over an episode. The default reward range is set to \((-\infty,+\infty)\).
spec - An environment spec that contains the information used to initialize the environment from gymnasium.make()
metadata - The metadata of the environment, i.e. render modes, render fps
np_random - The random number generator for the environment. This is automatically assigned during super().reset(seed=seed) and when assessing self.np_random.

scml.std.rl