MarlGroupMapType

torchrl.envs.MarlGroupMapType(value, names=None, *, module=None, qualname=None, type=None, start=1)

Marl 組對映型別。

作為 torchrl 多智慧體的一個特性，你能夠控制環境中智慧體的分組。你可以將智慧體分組（堆疊它們的張量），以便在透過同一個神經網路時利用向量化。你可以將智慧體拆分到不同的組中，如果它們是異構的或者應該由不同的神經網路處理。要進行分組，你只需在環境構建時傳遞一個 group_map。

否則，你可以從此類中選擇一種預設的分組策略。

• 對於 group_map=MarlGroupMapType.ALL_IN_ONE_GROUP 和智慧體 ["agent_0", "agent_1", "agent_2", "agent_3"]，進出你的環境的 tensordicts 將看起來像

  >>> print(env.rand_action(env.reset()))
  TensorDict(
      fields={
          agents: TensorDict(
              fields={
                  action: Tensor(shape=torch.Size([4, 9]), device=cpu, dtype=torch.int64, is_shared=False),
                  done: Tensor(shape=torch.Size([4, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                  observation: Tensor(shape=torch.Size([4, 3, 3, 2]), device=cpu, dtype=torch.int8, is_shared=False)},
              batch_size=torch.Size([4]))},
      batch_size=torch.Size([]))
  >>> print(env.group_map)
  {"agents": ["agent_0", "agent_1", "agent_2", "agent_3]}
  

• 對於 group_map=MarlGroupMapType.ONE_GROUP_PER_AGENT 和智慧體 ["agent_0", "agent_1", "agent_2", "agent_3"]，進出你的環境的 tensordicts 將看起來像

  >>> print(env.rand_action(env.reset()))
  TensorDict(
      fields={
          agent_0: TensorDict(
              fields={
                  action: Tensor(shape=torch.Size([9]), device=cpu, dtype=torch.int64, is_shared=False),
                  done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
                  observation: Tensor(shape=torch.Size([3, 3, 2]), device=cpu, dtype=torch.int8, is_shared=False)},
              batch_size=torch.Size([]))},
          agent_1: TensorDict(
              fields={
                  action: Tensor(shape=torch.Size([9]), device=cpu, dtype=torch.int64, is_shared=False),
                  done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
                  observation: Tensor(shape=torch.Size([3, 3, 2]), device=cpu, dtype=torch.int8, is_shared=False)},
              batch_size=torch.Size([]))},
          agent_2: TensorDict(
              fields={
                  action: Tensor(shape=torch.Size([9]), device=cpu, dtype=torch.int64, is_shared=False),
                  done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
                  observation: Tensor(shape=torch.Size([3, 3, 2]), device=cpu, dtype=torch.int8, is_shared=False)},
              batch_size=torch.Size([]))},
          agent_3: TensorDict(
              fields={
                  action: Tensor(shape=torch.Size([9]), device=cpu, dtype=torch.int64, is_shared=False),
                  done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
                  observation: Tensor(shape=torch.Size([3, 3, 2]), device=cpu, dtype=torch.int8, is_shared=False)},
              batch_size=torch.Size([]))},
      batch_size=torch.Size([]))
  >>> print(env.group_map)
  {"agent_0": ["agent_0"], "agent_1": ["agent_1"], "agent_2": ["agent_2"], "agent_3": ["agent_3"]}