memorax.networks.heads

Output heads for different RL objectives.

Policy Heads

Categorical - Categorical policy for discrete actions.

Gaussian - Gaussian policy for continuous actions.

SquashedGaussian - Squashed Gaussian policy (tanh-bounded).

Value Heads

VNetwork - State value function head.

DiscreteQNetwork - Q-network for discrete actions.

ContinuousQNetwork - Q-network for continuous actions.

Temperature

Alpha - Learnable temperature parameter for SAC.