def with_replaced_reward(self, new_r):
new_trajs = [
Trajectory(traj.obs_T_Do, traj.obsfeat_T_Df, traj.adist_T_Pa,
traj.a_T_Da, traj_new_r)
for traj, traj_new_r in util.safezip(self.trajs, new_r)
]
return TrajBatch(new_trajs, self.obs, self.obsfeat, self.adist, self.a,
new_r, self.time)
def __init__(self, arrays, lengths=None):
if lengths is None:
# Without provided lengths, `arrays` is interpreted as a list of arrays
# and self.lengths is set to the list of lengths for those arrays
self.arrays = arrays
self.stacked = np.concatenate(arrays, axis=0)
self.lengths = np.array([len(a) for a in arrays])
else:
# With provided lengths, `arrays` is interpreted as concatenated data
# and self.lengths is set to the provided lengths.
self.arrays = np.split(arrays, np.cumsum(lengths)[:-1])
self.stacked = arrays
self.lengths = np.asarray(lengths, dtype=int)
assert all(len(a) == l for a,l in util.safezip(self.arrays, self.lengths))
self.boundaries = np.concatenate([[0], np.cumsum(self.lengths)])
assert self.boundaries[-1] == len(self.stacked)
def __init__(self, arrays, lengths=None):
if lengths is None:
# Without provided lengths, `arrays` is interpreted as a list of arrays
# and self.lengths is set to the list of lengths for those arrays
self.arrays = arrays
self.stacked = np.concatenate(arrays, axis=0)
self.lengths = np.array([len(a) for a in arrays])
else:
# With provided lengths, `arrays` is interpreted as concatenated data
# and self.lengths is set to the provided lengths.
self.arrays = np.split(arrays, np.cumsum(lengths)[:-1])
self.stacked = arrays
self.lengths = np.asarray(lengths, dtype=int)
assert all(len(a) == l for a,l in util.safezip(self.arrays, self.lengths))
self.boundaries = np.concatenate([[0], np.cumsum(self.lengths)])
assert self.boundaries[-1] == len(self.stacked)
def with_replaced_reward(self, new_r):
new_trajseqs = [TrajSequence(trajseq.obs_s_T_Do, trajseq.obsfeat_T_Df, trajseq.adist_T_Pa, trajseq.a_T_Da, traj_new_r) for trajseq, traj_new_r in util.safezip(self.trajseqs, new_r)]
return TrajSeqBatch(new_trajseqs, self.obs, self.obsfeat, self.adist, self.a, new_r, self.m, self.seqlen)
def with_replaced_reward(self, new_r):
new_trajs = [Trajectory(traj.obs_T_Do, traj.obsfeat_T_Df, traj.adist_T_Pa, traj.a_T_Da, traj_new_r) for traj, traj_new_r in util.safezip(self.trajs, new_r)]
return TrajBatch(new_trajs, self.obs, self.obsfeat, self.adist, self.a, new_r, self.time)