def _compute_path_probs(paths, pol_dist_type=None, insert=True,
insert_key='a_logprobs'):
"""
Returns a N x T matrix of action probabilities
"""
if pol_dist_type is None:
# try to infer distribution type
path0 = paths[0]
if 'log_std' in path0['agent_infos']:
pol_dist_type = DIST_GAUSSIAN
elif 'prob' in path0['agent_infos']:
pol_dist_type = DIST_CATEGORICAL
else:
raise NotImplementedError()
# compute path probs
Npath = len(paths)
actions = [path['actions'] for path in paths]
if pol_dist_type == DIST_GAUSSIAN:
params = [(path['agent_infos']['mean'], path['agent_infos']['log_std']) for path in paths]
path_probs = [gauss_log_pdf(params[i], actions[i]) for i in range(Npath)]
elif pol_dist_type == DIST_CATEGORICAL:
params = [(path['agent_infos']['prob'],) for path in paths]
path_probs = [categorical_log_pdf(params[i], actions[i]) for i in range(Npath)]
else:
raise NotImplementedError("Unknown distribution type")
if insert:
for i, path in enumerate(paths):
path[insert_key] = path_probs[i]
return np.array(path_probs)
def _compute_path_probs(paths, pol_dist_type=None, insert=True,
insert_key='a_logprobs'):
"""
Returns a N x T matrix of action probabilities
"""
if pol_dist_type is None:
# try to infer distribution type
path0 = paths[0]
if 'log_std' in path0['agent_infos']:
pol_dist_type = DIST_GAUSSIAN
elif 'prob' in path0['agent_infos']:
pol_dist_type = DIST_CATEGORICAL
else:
raise NotImplementedError()
# compute path probs
Npath = len(paths)
actions = [path['actions'] for path in paths]
if pol_dist_type == DIST_GAUSSIAN:
params = [(path['agent_infos']['mean'], path['agent_infos']['log_std']) for path in paths]
path_probs = [gauss_log_pdf(params[i], actions[i]) for i in range(Npath)]
elif pol_dist_type == DIST_CATEGORICAL:
params = [(path['agent_infos']['prob'],) for path in paths]
path_probs = [categorical_log_pdf(params[i], actions[i]) for i in range(Npath)]
else:
raise NotImplementedError("Unknown distribution type")
if insert:
for i, path in enumerate(paths):
path[insert_key] = path_probs[i]
return np.array(path_probs)
