Monitor Wrapper¶
- class stable_baselines3.common.monitor.Monitor(env, filename=None, allow_early_resets=True, reset_keywords=(), info_keywords=())[source]¶
A monitor wrapper for Gym environments, it is used to know the episode reward, length, time and other data.
- Parameters:
env (
Env
) – The environmentfilename (
Optional
[str
]) – the location to save a log file, can be None for no logallow_early_resets (
bool
) – allows the reset of the environment before it is donereset_keywords (
Tuple
[str
,...
]) – extra keywords for the reset call, if extra parameters are needed at resetinfo_keywords (
Tuple
[str
,...
]) – extra information to log, from the information return of env.step()
- get_episode_lengths()[source]¶
Returns the number of timesteps of all the episodes
- Return type:
List
[int
]- Returns:
- get_episode_rewards()[source]¶
Returns the rewards of all the episodes
- Return type:
List
[float
]- Returns:
- get_episode_times()[source]¶
Returns the runtime in seconds of all the episodes
- Return type:
List
[float
]- Returns:
- reset(**kwargs)[source]¶
Calls the Gym environment reset. Can only be called if the environment is over, or if allow_early_resets is True
- Parameters:
kwargs – Extra keywords saved for the next episode. only if defined by reset_keywords
- Return type:
Union
[Tuple
,Dict
[str
,Any
],ndarray
,int
]- Returns:
the first observation of the environment
- class stable_baselines3.common.monitor.ResultsWriter(filename='', header=None, extra_keys=())[source]¶
A result writer that saves the data from the Monitor class
- Parameters:
filename (
str
) – the location to save a log file, can be None for no logheader (
Optional
[Dict
[str
,Union
[float
,str
]]]) – the header dictionary object of the saved csvreset_keywords – the extra information to log, typically is composed of
reset_keywords
andinfo_keywords