xpag.agents.flax_agents.td3.td3.TrainingState#

class TrainingState(policy_optimizer_state, policy_params, target_policy_params, q_optimizer_state, q_params, target_q_params, key, steps)#

Bases: object

Contains training state for the learner.

Methods

replace

"Returns a new object replacing the specified fields with new values.

Attributes

`policy_optimizer_state`
`policy_params`
`target_policy_params`
`q_optimizer_state`
`q_params`
`target_q_params`
`key`
`steps`

replace(**updates)#: “Returns a new object replacing the specified fields with new values.