gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix DummyVecEnv reusing buffers

Browse Source
This commit is contained in:
Alex Nichol
2018-03-02 17:18:07 -08:00
parent 569bd42629
commit 8b3a6c2051
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
baselines/common/vec_env/dummy_vec_env.py
View File

@@ -28,7 +28,8 @@ class DummyVecEnv(VecEnv):
self.buf_obs[t][i] = x self.buf_obs[t][i] = x
else: else:
self.buf_obs[0][i] = obs_tuple self.buf_obs[0][i] = obs_tuple
return self._obs_from_buf(), self.buf_rews, self.buf_dones, self.buf_infos return (self._obs_from_buf(), np.copy(self.buf_rews), np.copy(self.buf_dones),
self.buf_infos.copy())
def reset(self): def reset(self):
for i in range(self.num_envs): for i in range(self.num_envs):
@@ -45,6 +46,6 @@ class DummyVecEnv(VecEnv):
def _obs_from_buf(self): def _obs_from_buf(self):
if len(self.buf_obs) == 1: if len(self.buf_obs) == 1:
return self.buf_obs[0] return np.copy(self.buf_obs[0])
else: else:
return tuple(self.buf_obs) return tuple(np.copy(x) for x in self.buf_obs)

1
baselines/ddpg/training.py
View File

@@ -189,4 +189,3 @@ def train(env, nb_epochs, nb_epoch_cycles, render_eval, reward_scale, render, pa
if eval_env and hasattr(eval_env, 'get_state'): if eval_env and hasattr(eval_env, 'get_state'):
with open(os.path.join(logdir, 'eval_env_state.pkl'), 'wb') as f: with open(os.path.join(logdir, 'eval_env_state.pkl'), 'wb') as f:
pickle.dump(eval_env.get_state(), f) pickle.dump(eval_env.get_state(), f)