Data Processing and Replay Buffer¶
Process data stream from interactions.
-
class
jax_agents.common.data_processor.DataProcessor(n_steps, replay_buffer, folder)¶ Bases:
objectClass to process the data stream of states and actions.
Calculate the rewards and store 3 tuples (state, action, reward) in a deque in order to support multistep reinforcement learning (see https://arxiv.org/pdf/1901.07510.pdf). Then fill the replay buffer for off policy rl algorithms.
-
close()¶ Close logger file.
-
data_callback(normed_state, normed_action, reward, reset_flag, timestep)¶ Fill the deque and the replay buffer.
-