my_replay_buffer.py

import math, random

import gym
import numpy as np
from common.wrappers import make_atari, wrap_deepmind, wrap_pytorch
import torch
import torch.nn as nn
import torch.optim as optim
 
import torch.nn.functional as F
from IPython.display import clear_output
import matplotlib.pyplot as plt
from collections import deque

USE_CUDA = torch.cuda.is_available()
Variable = lambda *args, **kwargs: autograd.Variable(*args, **kwargs).cuda() if USE_CUDA else autograd.Variable(*args, **kwargs)



class ReplayBuffer(object):
    def __init__(self, capacity):
        self.buffer = deque(maxlen=capacity)
                        
    def push(self, state, action, reward, next_state, done):
        state      = np.expand_dims(state, 0)
        next_state = np.expand_dims(next_state, 0)
                                                            
        self.buffer.append((state, action, reward, next_state, done))
                                                                        
    def sample(self, batch_size):
        state, action, reward, next_state, done = zip(*random.sample(self.buffer, batch_size))
        return np.concatenate(state), action, reward, np.concatenate(next_state), done
                                                                                                
    def __len__(self):
        return len(self.buffer)

class NaivePrioritizedBuffer(object):
    def __init__(self, capacity, prob_alpha=0.6):
        self.prob_alpha = prob_alpha
        self.capacity   = capacity
        self.buffer     = []
        self.pos        = 0
        self.priorities = np.zeros((capacity,), dtype=np.float32)
    
    def push(self, state, action, reward, next_state, done):
        assert state.ndim == next_state.ndim
        state      = np.expand_dims(state, 0)
        next_state = np.expand_dims(next_state, 0)
        
        max_prio = self.priorities.max() if self.buffer else 1.0
        
        if len(self.buffer) < self.capacity:
            self.buffer.append((state, action, reward, next_state, done))
        else:
            self.buffer[self.pos] = (state, action, reward, next_state, done)
        
        self.priorities[self.pos] = max_prio
        self.pos = (self.pos + 1) % self.capacity
    
    def sample(self, batch_size, beta=0.4):
        if len(self.buffer) == self.capacity:
            prios = self.priorities
        else:
            prios = self.priorities[:self.pos]
        
        probs  = prios ** self.prob_alpha
        probs /= probs.sum()
        
        indices = np.random.choice(len(self.buffer), batch_size, p=probs)
        samples = [self.buffer[idx] for idx in indices]
        
        total    = len(self.buffer)
        weights  = (total * probs[indices]) ** (-beta)
        weights /= weights.max()
        weights  = np.array(weights, dtype=np.float32)
        
        batch       = list(zip(*samples))
        states      = np.concatenate(batch[0])
        actions     = batch[1]
        rewards     = batch[2]
        next_states = np.concatenate(batch[3])
        dones       = batch[4]
        
        return states, actions, rewards, next_states, dones, indices, weights
        
    def update_priorities(self, batch_indices, batch_priorities):
        for idx, prio in zip(batch_indices, batch_priorities):
            self.priorities[idx] = prio
    
    def __len__(self):
        return len(self.buffer)