diff --git a/baselines/common/cmd_util.py b/baselines/common/cmd_util.py index f20809e..db395a7 100644 --- a/baselines/common/cmd_util.py +++ b/baselines/common/cmd_util.py @@ -29,7 +29,10 @@ def make_vec_env(env_id, env_type, num_env, seed, wrapper_kwargs=None, start_ind def _thunk(): env = make_atari(env_id) if env_type == 'atari' else gym.make(env_id) env.seed(seed + 10000*mpi_rank + rank if seed is not None else None) - env = Monitor(env, logger.get_dir() and os.path.join(logger.get_dir(), str(mpi_rank) + '.' + str(rank))) + env = Monitor(env, + logger.get_dir() and os.path.join(logger.get_dir(), str(mpi_rank) + '.' + str(rank)) + allow_early_resets=True) + if env_type == 'atari': return wrap_deepmind(env, **wrapper_kwargs) elif reward_scale != 1: return RewardScaler(env, reward_scale) else: return env