dodox/metastable-baselines
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Reverting last two commits (was ugly hack)

Browse Source
This commit is contained in:
Dominik Moritz Roth 2023-01-26 17:43:57 +01:00
parent 6f1837bda5
commit 20646f07f3
1 changed files with 0 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
metastable_baselines/misc/rollout_buffer.py
View File

@ -228,14 +228,6 @@ class GaussianRolloutCollectorAuxclass():
actions, self.action_space.low, self.action_space.high)
new_obs, rewards, dones, infos = env.step(clipped_actions)
if 'episode_end' in infos[0]:
for i in range(len(infos)):
if infos[i]['episode_end'] and 'episode' not in infos:
infos[i]['episode'] = {'r': rewards[i]}
if len(infos) and 'r' not in infos[0]:
for i in range(len(infos)):
if 'r' not in infos[i]:
infos[i]['r'] = rewards[i]
self.num_timesteps += env.num_envs
@ -282,20 +274,3 @@ class GaussianRolloutCollectorAuxclass():
callback.on_rollout_end()
return True
def _update_info_buffer(self, infos: List[Dict[str, Any]], dones: Optional[np.ndarray] = None) -> None:
"""
Retrieve reward, episode length, episode success and update the buffer
if using Monitor wrapper or a GoalEnv.
:param infos: List of additional information about the transition.
:param dones: Termination signals
"""
if dones is None:
dones = np.array([False] * len(infos))
for idx, info in enumerate(infos):
maybe_ep_info = info.get("episode")
maybe_is_success = info.get("is_success")
if maybe_ep_info is not None:
self.ep_info_buffer.extend([maybe_ep_info])
if maybe_is_success is not None and dones[idx]:
self.ep_success_buffer.append(maybe_is_success)