`rb.sample(n)` yields an index out of bound error
This is a follow up on #108 (closed). The following code yields a IndexError: index 1 is out of bounds for axis 0 with size 1 error.
import numpy as np
from collections import deque
import gym
from gym import spaces
import cv2
cv2.ocl.setUseOpenCL(False)
class NoopResetEnv(gym.Wrapper):
def __init__(self, env, noop_max=30):
"""Sample initial states by taking random number of no-ops on reset.
No-op is assumed to be action 0.
"""
gym.Wrapper.__init__(self, env)
self.noop_max = noop_max
self.override_num_noops = None
self.noop_action = 0
assert env.unwrapped.get_action_meanings()[0] == 'NOOP'
def reset(self, **kwargs):
""" Do no-op action for a number of steps in [1, noop_max]."""
self.env.reset(**kwargs)
if self.override_num_noops is not None:
noops = self.override_num_noops
else:
noops = self.unwrapped.np_random.randint(1, self.noop_max + 1) #pylint: disable=E1101
assert noops > 0
obs = None
for _ in range(noops):
obs, _, done, _ = self.env.step(self.noop_action)
if done:
obs = self.env.reset(**kwargs)
return obs
def step(self, ac):
return self.env.step(ac)
class FireResetEnv(gym.Wrapper):
def __init__(self, env):
"""Take action on reset for environments that are fixed until firing."""
gym.Wrapper.__init__(self, env)
assert env.unwrapped.get_action_meanings()[1] == 'FIRE'
assert len(env.unwrapped.get_action_meanings()) >= 3
def reset(self, **kwargs):
self.env.reset(**kwargs)
obs, _, done, _ = self.env.step(1)
if done:
self.env.reset(**kwargs)
obs, _, done, _ = self.env.step(2)
if done:
self.env.reset(**kwargs)
return obs
def step(self, ac):
return self.env.step(ac)
class EpisodicLifeEnv(gym.Wrapper):
def __init__(self, env):
"""Make end-of-life == end-of-episode, but only reset on true game over.
Done by DeepMind for the DQN and co. since it helps value estimation.
"""
gym.Wrapper.__init__(self, env)
self.lives = 0
self.was_real_done = True
def step(self, action):
obs, reward, done, info = self.env.step(action)
self.was_real_done = done
# check current lives, make loss of life terminal,
# then update lives to handle bonus lives
lives = self.env.unwrapped.ale.lives()
if lives < self.lives and lives > 0:
# for Qbert sometimes we stay in lives == 0 condition for a few frames
# so it's important to keep lives > 0, so that we only reset once
# the environment advertises done.
done = True
self.lives = lives
return obs, reward, done, info
def reset(self, **kwargs):
"""Reset only when lives are exhausted.
This way all states are still reachable even though lives are episodic,
and the learner need not know about any of this behind-the-scenes.
"""
if self.was_real_done:
obs = self.env.reset(**kwargs)
else:
# no-op step to advance from terminal/lost life state
obs, _, _, _ = self.env.step(0)
self.lives = self.env.unwrapped.ale.lives()
return obs
class MaxAndSkipEnv(gym.Wrapper):
def __init__(self, env, skip=4):
"""Return only every `skip`-th frame"""
gym.Wrapper.__init__(self, env)
# most recent raw observations (for max pooling across time steps)
self._obs_buffer = np.zeros((2,)+env.observation_space.shape, dtype=np.uint8)
self._skip = skip
def step(self, action):
"""Repeat action, sum reward, and max over last observations."""
total_reward = 0.0
done = None
for i in range(self._skip):
obs, reward, done, info = self.env.step(action)
if i == self._skip - 2: self._obs_buffer[0] = obs
if i == self._skip - 1: self._obs_buffer[1] = obs
total_reward += reward
if done:
break
# Note that the observation on the done=True frame
# doesn't matter
max_frame = self._obs_buffer.max(axis=0)
return max_frame, total_reward, done, info
def reset(self, **kwargs):
return self.env.reset(**kwargs)
class ClipRewardEnv(gym.RewardWrapper):
def __init__(self, env):
gym.RewardWrapper.__init__(self, env)
def reward(self, reward):
"""Bin reward to {+1, 0, -1} by its sign."""
return np.sign(reward)
class WarpFrame(gym.ObservationWrapper):
def __init__(self, env, width=84, height=84, grayscale=True, dict_space_key=None):
"""
Warp frames to 84x84 as done in the Nature paper and later work.
If the environment uses dictionary observations, `dict_space_key` can be specified which indicates which
observation should be warped.
"""
super().__init__(env)
self._width = width
self._height = height
self._grayscale = grayscale
self._key = dict_space_key
if self._grayscale:
num_colors = 1
else:
num_colors = 3
new_space = gym.spaces.Box(
low=0,
high=255,
shape=(self._height, self._width, num_colors),
dtype=np.uint8,
)
if self._key is None:
original_space = self.observation_space
self.observation_space = new_space
else:
original_space = self.observation_space.spaces[self._key]
self.observation_space.spaces[self._key] = new_space
assert original_space.dtype == np.uint8 and len(original_space.shape) == 3
def observation(self, obs):
if self._key is None:
frame = obs
else:
frame = obs[self._key]
if self._grayscale:
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
frame = cv2.resize(
frame, (self._width, self._height), interpolation=cv2.INTER_AREA
)
if self._grayscale:
frame = np.expand_dims(frame, -1)
if self._key is None:
obs = frame
else:
obs = obs.copy()
obs[self._key] = frame
return obs
class FrameStack(gym.Wrapper):
def __init__(self, env, k):
"""Stack k last frames.
Returns lazy array, which is much more memory efficient.
See Also
--------
baselines.common.atari_wrappers.LazyFrames
"""
gym.Wrapper.__init__(self, env)
self.k = k
self.frames = deque([], maxlen=k)
shp = env.observation_space.shape
self.observation_space = spaces.Box(low=0, high=255, shape=((shp[0] * k,)+shp[1:]), dtype=env.observation_space.dtype)
def reset(self):
ob = self.env.reset()
for _ in range(self.k):
self.frames.append(ob)
return self._get_ob()
def step(self, action):
ob, reward, done, info = self.env.step(action)
self.frames.append(ob)
return self._get_ob(), reward, done, info
def _get_ob(self):
assert len(self.frames) == self.k
return np.concatenate(list(self.frames), axis=-1)
class ScaledFloatFrame(gym.ObservationWrapper):
def __init__(self, env):
gym.ObservationWrapper.__init__(self, env)
self.observation_space = gym.spaces.Box(low=0, high=1, shape=env.observation_space.shape, dtype=np.float32)
def observation(self, observation):
# careful! This undoes the memory optimization, use
# with smaller replay buffers only.
return np.array(observation).astype(np.float32) / 255.0
class LazyFrames(object):
def __init__(self, frames):
"""This object ensures that common frames between the observations are only stored once.
It exists purely to optimize memory usage which can be huge for DQN's 1M frames replay
buffers.
This object should only be converted to numpy array before being passed to the model.
You'd not believe how complex the previous solution was."""
self._frames = frames
self._out = None
def _force(self):
if self._out is None:
self._out = np.concatenate(self._frames, axis=0)
self._frames = None
return self._out
def __array__(self, dtype=None):
out = self._force()
if dtype is not None:
out = out.astype(dtype)
return out
def __len__(self):
return len(self._force())
def __getitem__(self, i):
return self._force()[i]
def count(self):
frames = self._force()
return frames.shape[frames.ndim - 1]
def frame(self, i):
return self._force()[..., i]
def wrap_atari(env, max_episode_steps=None):
assert 'NoFrameskip' in env.spec.id
env = NoopResetEnv(env, noop_max=30)
env = MaxAndSkipEnv(env, skip=4)
assert max_episode_steps is None
return env
class ImageToPyTorch(gym.ObservationWrapper):
"""
Image shape to channels x weight x height
"""
def __init__(self, env):
super(ImageToPyTorch, self).__init__(env)
old_shape = self.observation_space.shape
self.observation_space = gym.spaces.Box(
low=0,
high=255,
shape=(old_shape[-1], old_shape[0], old_shape[1]),
dtype=np.uint8,
)
def observation(self, observation):
return np.transpose(observation, axes=(2, 0, 1))
def wrap_deepmind(env, episode_life=True, clip_rewards=True, frame_stack=False, scale=False):
"""Configure environment for DeepMind-style Atari.
"""
if episode_life:
env = EpisodicLifeEnv(env)
if 'FIRE' in env.unwrapped.get_action_meanings():
env = FireResetEnv(env)
env = WarpFrame(env)
if scale:
env = ScaledFloatFrame(env)
if clip_rewards:
env = ClipRewardEnv(env)
# env = ImageToPyTorch(env)
if frame_stack:
env = FrameStack(env, 4)
return env
from cpprb import ReplayBuffer, PrioritizedReplayBuffer
import numpy as np
env = gym.make("PongNoFrameskip-v4")
env = wrap_atari(env)
env = gym.wrappers.RecordEpisodeStatistics(env) # records episode reward in `info['episode']['r']`
env = wrap_deepmind(
env,
clip_rewards=True,
frame_stack=True,
scale=False,
)
env.seed(3)
env.action_space.seed(3)
obs = env.reset()
rb = ReplayBuffer(32,{"obs":{"shape": (84,84,4)}, 'rew': {}, 'act': {}, 'done': {}},
next_of = "obs", stack_compress = "obs")
obs = env.reset()
obss = []
for i in range(2):
obs = np.array(obs)
obss += [obs]
action = env.action_space.sample()
next_obs, reward, done, info = env.step(action)
rb.add(obs=obs,
next_obs=next_obs,
act=action,
rew=reward,
done=float(done))
obs = next_obs
obss += [next_obs]
rb.on_episode_end()
print("actual sequences")
for o in obss:
print(o.sum())
print("sampled obs, next_obs")
sample = rb.sample(1)
sample = rb.sample(1)
sample = rb.sample(1)
sample = rb.sample(1)
sample = rb.sample(1)
for o, o2 in zip(sample["obs"], sample["next_obs"]):
print(o.sum(), o2.sum())
print("====================================================")
# assumes the env is done
done = True
if done:
obs = env.reset()
for i in range(2):
obs = np.array(obs)
obss += [obs]
action = env.action_space.sample()
next_obs, reward, done, info = env.step(action)
rb.add(obs=obs,
next_obs=next_obs,
act=action,
rew=reward,
done=float(done))
obs = next_obs
obss += [next_obs]
print("actual sequences")
for o in obss:
print(o.sum())
print("sampled obs, next_obs")
sample = rb.get_all_transitions()
for o, o2 in zip(sample["obs"], sample["next_obs"]):
print(o.sum(), o2.sum())
print("=====================================")
rb.on_episode_end()
print("sampled obs, next_obs")
sample = rb.get_all_transitions()
for o, o2 in zip(sample["obs"], sample["next_obs"]):
print(o.sum(), o2.sum())Edited by Costa Huang