A high-performance distributed training framework for Reinforcement Learning
save
and restore
APIs in parl.Agent
.parl.remote
.get_params
and set_params
to support getting parameters from parl.Model
, parl.Algorithm
and parl.Agent
.parl.algorithms
.Model
, Algorithm
and Agent
abstractions.sync_params_to
API in Model
to synchronize parameters between model and target model directly.