mirror of
https://github.com/wassname/pytorch-soft-actor-critic.git
synced 2026-06-27 16:46:28 +08:00
Pranjal Tandon
24 lines
768 B
Python
24 lines
768 B
Python
import random
|
|
import numpy as np
|
|
from collections import namedtuple
|
|
|
|
|
|
class ReplayMemory:
|
|
def __init__(self, capacity):
|
|
self.capacity = capacity
|
|
self.buffer = []
|
|
self.position = 0
|
|
|
|
def push(self, state, action, reward, next_state, done):
|
|
if len(self.buffer) < self.capacity:
|
|
self.buffer.append(None)
|
|
self.buffer[self.position] = (state, action, reward, next_state, done)
|
|
self.position = (self.position + 1) % self.capacity
|
|
|
|
def sample(self, batch_size):
|
|
batch = random.sample(self.buffer, batch_size)
|
|
state, action, reward, next_state, done = map(np.stack, zip(*batch))
|
|
return state, action, reward, next_state, done
|
|
|
|
def __len__(self):
|
|
return len(self.buffer) |