RL (gCastle)

Module name	gcastle_rl
Package	gCastle
Version	1.0.3
Language	Python
Docs	here
Paper	Zhu et al.[1], Zhang et al.[2]
Graph type	DAG
MCMC	No
Edge constraints	No
Data type	C
Data missingness
Intervention type
Docker	bpimages/gcastle:1.0.3

Causal discovery with reinforcement learning

A RL-based algorithm that can work with flexible score functions (including non-smooth ones).

Example JSON

[
  {
    "id": "gcastle_rl",
    "encoder_type": "TransformerEncoder",
    "hidden_dim": 64,
    "num_heads": 16,
    "num_stacks": 6,
    "residual": false,
    "decoder_type": "SingleLayerDecoder",
    "decoder_activation": "tanh",
    "decoder_hidden_dim": 16,
    "use_bias": false,
    "use_bias_constant": false,
    "bias_initial_value": false,
    "batch_size": 64,
    "input_dimension": 64,
    "normalize": false,
    "transpose": false,
    "score_type": "BIC",
    "reg_type": "LR",
    "lambda_iter_num": 1000,
    "lambda_flag_default": true,
    "score_bd_tight": false,
    "lambda2_update": 10,
    "score_lower": 0.0,
    "score_upper": 0.0,
    "nb_epoch": 20,
    "lr1_start": 0.001,
    "lr1_decay_step": 5000,
    "lr1_decay_rate": 0.96,
    "alpha": 0.99,
    "init_baseline": -1.0,
    "l1_graph_reg": 0.0,
    "verbose": false,
    "device_type": "cpu",
    "device_ids": 0,
    "timeout": null
  }
]