ray.rllib.policy.sample_batch.SampleBatch

class ray.rllib.policy.sample_batch.SampleBatch(*args, **kwargs)

Bases: dict

Wrapper around a dictionary with string keys and array-like values.

For example, {“obs”: [1, 2, 3], “reward”: [0, -1, 1]} is a batch of three samples, each with an “obs” and “reward” attribute.

Methods

__init__(*args, **kwargs)	Constructs a sample batch (same params as dict constructor).
agent_steps()	Returns the same as len(self) (number of steps in this batch).
as_multi_agent()	Returns the respective MultiAgentBatch using DEFAULT_POLICY_ID.
clear()
columns(keys)	Returns a list of the batch-data in the specified columns.
compress([bulk, columns])	Compresses the data buffers (by column) in place.
concat(other)	Concatenates other to this one and returns a new SampleBatch.
copy([shallow])	Creates a deep or shallow copy of this SampleBatch and returns it.
decompress_if_needed([columns])	Decompresses data buffers (per column if not compressed) in place.
env_steps()	Returns the same as len(self) (number of steps in this batch).
fromkeys([value])	Create a new dictionary with keys from iterable and values set to value.
get(key[, default])	Returns one column (by key) from the data or a default value.
get_single_step_input_dict(view_requirements)	Creates single ts SampleBatch at given index from self.
is_single_trajectory()	Returns True if this SampleBatch only contains one trajectory.
is_terminated_or_truncated()	Returns True if self is either terminated or truncated at idx -1.
items()
keys()
pop(k[,d])	If key is not found, default is returned if given, otherwise KeyError is raised
popitem()	Remove and return a (key, value) pair as a 2-tuple.
right_zero_pad(max_seq_len[, exclude_states])	Right (adding zeros at end) zero-pads this SampleBatch in-place.
rows()	Returns an iterator over data rows, i.e. dicts with column values.
set_get_interceptor(fn)	Sets a function to be called on every getitem.
set_training([training])	Sets the is_training flag for this SampleBatch.
setdefault(key[, default])	Insert key with a value of default if key is not in the dictionary.
shuffle()	Shuffles the rows of this batch in-place.
size_bytes()	Returns sum over number of bytes of all data buffers.
slice(start, end[, state_start, state_end])	Returns a slice of the row data of this batch (w/o copying).
split_by_episode([key])	Splits by eps_id column and returns list of new batches.
timeslices([size, num_slices, k])	Returns SampleBatches, each one representing a k-slice of this one.
to_device(device[, framework])	TODO: transfer batch to given device as framework tensor.
update([E, ]**F)	If E is present and has a .keys() method, then does: for k in E: D[k] = E[k] If E is present and lacks a .keys() method, then does: for k, v in E: D[k] = v In either case, this is followed by: for k in F: D[k] = F[k]
values()

Attributes

ACTIONS
ACTION_DIST
ACTION_DIST_INPUTS
ACTION_LOGP
ACTION_PROB
AGENT_INDEX
ATTENTION_MASKS
CUR_OBS
DONES
ENV_ID
EPS_ID
INFOS
NEXT_OBS
OBS
OBS_EMBEDS
PREV_ACTIONS
PREV_REWARDS
RETURNS_TO_GO
REWARDS
SEQ_LENS
T
TERMINATEDS
TRUNCATEDS
UNROLL_ID
VALUES_BOOTSTRAPPED
VF_PREDS
is_training