Add a sb3 algo + policy for domains with graph observations

[nhuet]

• we reuse our stable_baselines3 wrapper
• the policy is extracting features from the graph with a GNN
• the GNN is using pytorch-geometric
• We subclass
  • ActorCriticPolicy:
    • feature extractor = gnn
    • custom conversion of observation to torch to convert into torch_geometric.data.Data
  • PPO to handle properly
    • observation conversion
    • rollout buffer
• Current limitations:
  • we extract a fixed number of features (independent of edge/node numbers) for now as we end with a feature reduction layer connected to a classic mlp (not knowning anything about the current graph structure)
• User input: the user can define (and default choices are made else)
  • the gnn (default to a 2 layers GCN), taking as inputs w.r.t torch_geometric conventions:
    • x: nodes features
    • edge_index: edge indices or sparse transposed adjency matrix
    • edge_attr (optional): edges features
    • edge_weight (optional): edge weights (taken from first dimension of edge_attr)
  • the feature reduction layer from the gnn output to the fixed number of features (default to global_max_pool + linear layer + relu)

We also introduce a multiinput policy to take into account (for instance) static graph features. The observation space in that case is a DictSpace whose subspaces can contain some Graph spaces.