Merge remote-tracking branch 'openai-gym/master'

# Conflicts:
#	gym/core.py
#	gym/envs/toy_text/cliffwalking.py
#	gym/envs/toy_text/frozen_lake.py
#	gym/wrappers/monitoring/video_recorder.py
#	gym/wrappers/pixel_observation.py

gym/core.py

@@ -1,4 +1,6 @@
 """Core API for Environment, Wrapper, ActionWrapper, RewardWrapper and ObservationWrapper."""
+import sys
+from typing import Generic, Optional, SupportsFloat, Tuple, TypeVar, Union
 from __future__ import annotations
 
 from abc import abstractmethod
@@ -179,7 +181,6 @@ def reset(
         if seed is not None:
             self._np_random, seed = seeding.np_random(seed)
 
-    @abstractmethod
     # TODO: remove kwarg mode with gym 1.0
     def render(self, mode="human") -> Optional[Union[RenderFrame, List[RenderFrame]]]:
         """Compute the render frames as specified by render_mode attribute during initialization of the environment.

gym/envs/toy_text/cliffwalking.py

@@ -96,12 +96,8 @@ def __init__(self, render_mode: Optional[str] = None):
         self.render_mode = render_mode
         self.renderer = Renderer(self.render_mode, self._render)
 
-    def _limit_coordinates(self, coord):
-        """
-        Prevent the agent from falling out of the grid world
-        :param coord:
-        :return:
-        """
+    def _limit_coordinates(self, coord: np.ndarray) -> np.ndarray:
+        """Prevent the agent from falling out of the grid world."""
         coord[0] = min(coord[0], self.shape[0] - 1)
         coord[0] = max(coord[0], 0)
         coord[1] = min(coord[1], self.shape[1] - 1)

gym/envs/toy_text/frozen_lake.py

@@ -73,39 +73,53 @@ def is_valid(res):
 
 class FrozenLakeEnv(Env):
     """
-    Frozen lake involves crossing a frozen lake from Start(S) to Goal(G) without falling into any Holes(H) by walking over
-    the Frozen(F) lake. The agent may not always move in the intended direction due to the slippery nature of the frozen lake.
+    Frozen lake involves crossing a frozen lake from Start(S) to Goal(G) without falling into any Holes(H)
+    by walking over the Frozen(F) lake.
+    The agent may not always move in the intended direction due to the slippery nature of the frozen lake.
+
+
     ### Action Space
     The agent takes a 1-element vector for actions.
     The action space is `(dir)`, where `dir` decides direction to move in which can be:
+
     - 0: LEFT
     - 1: DOWN
     - 2: RIGHT
     - 3: UP
+
     ### Observation Space
     The observation is a value representing the agent's current position as
     current_row * nrows + current_col (where both the row and col start at 0).
     For example, the goal position in the 4x4 map can be calculated as follows: 3 * 4 + 3 = 15.
     The number of possible observations is dependent on the size of the map.
     For example, the 4x4 map has 16 possible observations.
+
     ### Rewards
+
     Reward schedule:
     - Reach goal(G): +1
     - Reach hole(H): 0
     - Reach frozen(F): 0
+
     ### Arguments
+
     ```
     gym.make('FrozenLake-v1', desc=None,map_name="4x4", is_slippery=True)
     ```
+
     `desc`: Used to specify custom map for frozen lake. For example,
+
         desc=["SFFF", "FHFH", "FFFH", "HFFG"].
+
     `map_name`: ID to use any of the preloaded maps.
+
         "4x4":[
             "SFFF",
             "FHFH",
             "FFFH",
             "HFFG"
             ]
+
         "8x8": [
             "SFFFFFFF",
             "FFFFFFFF",
@@ -116,13 +130,16 @@ class FrozenLakeEnv(Env):
             "FHFFHFHF",
             "FFFHFFFG",
         ]
+
     `is_slippery`: True/False. If True will move in intended direction with
     probability of 1/3 else will move in either perpendicular direction with
     equal probability of 1/3 in both directions.
+
         For example, if action is left and is_slippery is True, then:
         - P(move left)=1/3
         - P(move up)=1/3
         - P(move down)=1/3
+
     ### Version History
     * v1: Bug fixes to rewards
     * v0: Initial versions release (1.0.0)

gym/wrappers/pixel_observation.py

@@ -2,7 +2,7 @@
 import collections
 import copy
 from collections.abc import MutableMapping
-from typing import Any, List, Optional
+from typing import Any, Dict, List, Optional, Tuple
 
 import numpy as np