Value Networks and Critics

Value networks estimate the value of states or state-action pairs.

ValueOperator(*args, **kwargs)	General class for value functions in RL.
DuelingCnnDQNet(out_features[, ...])	Dueling CNN Q-network.
DistributionalDQNnet(*args, **kwargs)	Distributional Deep Q-Network softmax layer.
ConvNet(in_features, depth, num_cells, ...)	A convolutional neural network.
MLP(in_features, out_features, depth, ...)	A multi-layer perceptron.
DdpgCnnActor(action_dim[, conv_net_kwargs, ...])	DDPG Convolutional Actor class.
DdpgCnnQNet([conv_net_kwargs, ...])	DDPG Convolutional Q-value class.
DdpgMlpActor(action_dim[, mlp_net_kwargs, ...])	DDPG Actor class.
DdpgMlpQNet([mlp_net_kwargs_net1, ...])	DDPG Q-value MLP class.
LSTMModule(*args, **kwargs)	An embedder for an LSTM module.
GRUModule(*args, **kwargs)	An embedder for an GRU module.
OnlineDTActor(state_dim, action_dim[, ...])	Online Decision Transformer Actor class.
DTActor(state_dim, action_dim[, ...])	Decision Transformer Actor class.
DecisionTransformer(state_dim, action_dim[, ...])	Online Decision Transformer.