|View source on GitHub|
Twin Delayed Deep Deterministic policy gradient (TD3) agent.
TD3 extends DDPG by adding an extra critic network and using the minimum of the two critic values to reduce overestimation bias.
"Addressing Function Approximation Error in Actor-Critic Methods" by Fujimoto et al.
For the full paper, see https://arxiv.org/abs/1802.09477
class Td3Agent: A TD3 Agent.
class Td3Info: Td3Info(actor_loss, critic_loss)