fix typos (#223)

all/bodies/_body.py

@@ -3,7 +3,7 @@
 
 class Body(Agent):
     """
-    A Body wraps a reinforcment learning Agent, altering its inputs and ouputs.
+    A Body wraps a reinforcement learning Agent, altering its inputs and outputs.
 
     The Body API is identical to the Agent API from the perspective of the
     rest of the system. This base class is provided only for semantic clarity.

all/environments/_environment.py

@@ -22,7 +22,7 @@ def name(self):
     @abstractmethod
     def reset(self):
         """
-        Reset the environment and return a new intial state.
+        Reset the environment and return a new initial state.
 
         Returns
         -------
@@ -58,7 +58,7 @@ def render(self, **kwargs):
     @abstractmethod
     def close(self):
         """
-        Clean up any extraneaous environment objects.
+        Clean up any extraneous environment objects.
         """
 
     @property
@@ -83,7 +83,7 @@ def state_space(self):
     @property
     def observation_space(self):
         """
-        Alias for Environemnt.state_space.
+        Alias for Environment.state_space.
 
         Returns
         -------

all/environments/_multiagent_environment.py

@@ -15,7 +15,7 @@ class MultiagentEnvironment(ABC):
     @abstractmethod
     def reset(self):
         '''
-        Reset the environment and return a new intial state for the first agent.
+        Reset the environment and return a new initial state for the first agent.
 
         Returns
             all.core.MultiagentState: The initial state for the next episode.
@@ -39,7 +39,7 @@ def render(self, **kwargs):
 
     @abstractmethod
     def close(self):
-        '''Clean up any extraneaous environment objects.'''
+        '''Clean up any extraneous environment objects.'''
 
     @abstractmethod
     def agent_iter(self):

all/environments/multiagent_pettingzoo.py

@@ -32,7 +32,7 @@ def __init__(self, zoo_env, name, device='cuda'):
         }
 
     '''
-    Reset the environment and return a new intial state.
+    Reset the environment and return a new initial state.
 
     Returns:
         An initial MultiagentState object.
@@ -43,7 +43,7 @@ def reset(self):
         return self.last()
 
     '''
-    Reset the environment and return a new intial state.
+    Reset the environment and return a new initial state.
 
     Args:
         action (int): An int or tensor containing a single integer representing the action.

all/experiments/experiment.py

@@ -38,7 +38,7 @@ def test(self, episodes=100):
         Test the agent in eval mode for a certain number of episodes.
 
         Args:
-            episodes (int): The number of test epsiodes.
+            episodes (int): The number of test episodes.
 
         Returns:
             list(float): A list of all returns received during testing.

all/experiments/multiagent_env_experiment.py

@@ -71,7 +71,7 @@ def train(self, frames=np.inf, episodes=np.inf):
     Test the agent in eval mode for a certain number of episodes.
 
     Args:
-        episodes (int): The number of test epsiodes.
+        episodes (int): The number of test episodes.
 
     Returns:
         list(float): A list of all returns received during testing.

all/memory/segment_tree.py

@@ -15,7 +15,7 @@ def __init__(self, capacity, operation, neutral_element):
                operation which reduces `operation` over
                a contiguous subsequence of items in the
                array.
-        Paramters
+        Parameters
         ---------
         capacity: int
             Total size of the array - must be a power of two.
@@ -108,7 +108,7 @@ def find_prefixsum_idx(self, prefixsum):
         Parameters
         ----------
         perfixsum: float
-            upperbound on the sum of array prefix
+            upper bound on the sum of array prefix
         Returns
         -------
         idx: int

all/nn/__init__.py

@@ -27,8 +27,8 @@ class Aggregation(nn.Module):
     https://arxiv.org/abs/1511.06581
     This layer computes a Q function by combining
     an estimate of V with an estimate of the advantage.
-    The advantage is normalized by substracting the average
-    advantage so that we can propertly
+    The advantage is normalized by subtracting the average
+    advantage so that we can properly
     """
 
     def forward(self, value, advantages):

all/policies/greedy.py

@@ -8,7 +8,7 @@ class GreedyPolicy(Schedulable):
     An  "epsilon-greedy" action selection policy for discrete action spaces.
 
     This policy will usually choose the optimal action according to an approximation
-    of the action value function (the "q-function"), but with probabilty epsilon will
+    of the action value function (the "q-function"), but with probability epsilon will
     choose a random action instead. GreedyPolicy is a Schedulable, meaning that
     epsilon can be varied over time by passing a Scheduler object.
 
@@ -47,7 +47,7 @@ class ParallelGreedyPolicy(Schedulable):
     A parallel version of the "epsilon-greedy" action selection policy for discrete action spaces.
 
     This policy will usually choose the optimal action according to an approximation
-    of the action value function (the "q-function"), but with probabilty epsilon will
+    of the action value function (the "q-function"), but with probability epsilon will
     choose a random action instead. GreedyPolicy is a Schedulable, meaning that
     epsilon can be varied over time by passing a Scheduler object.
 

all/presets/atari/c51.py

@@ -64,7 +64,7 @@ class C51AtariPreset(Preset):
         atoms (int): The number of atoms in the categorical distribution used to represent
             the distributional value function.
         v_min (int): The expected return corresponding to the smallest atom.
-        v_max (int): The expected return correspodning to the larget atom.
+        v_max (int): The expected return corresponding to the largest atom.
         model_constructor (function): The function used to construct the neural model.
     """
 

all/presets/atari/ppo.py

@@ -57,7 +57,7 @@ class PPOAtariPreset(ParallelPreset):
         value_loss_scaling (float): Coefficient for the value function loss.
         clip_initial (float): Value for epsilon in the clipped PPO objective function at the beginning of training.
         clip_final (float): Value for epsilon in the clipped PPO objective function at the end of training.
-        epochs (int): Number of times to iterature through each batch.
+        epochs (int): Number of times to literature through each batch.
         minibatches (int): The number of minibatches to split each batch into.
         n_envs (int): Number of parallel actors.
         n_steps (int): Length of each rollout.

all/presets/atari/rainbow.py

@@ -72,7 +72,7 @@ class RainbowAtariPreset(Preset):
         atoms (int): The number of atoms in the categorical distribution used to represent
             the distributional value function.
         v_min (int): The expected return corresponding to the smallest atom.
-        v_max (int): The expected return correspodning to the larget atom.
+        v_max (int): The expected return corresponding to the largest atom.
         sigma (float): Initial noisy network noise.
         model_constructor (function): The function used to construct the neural model.
     """

all/presets/classic_control/ppo.py

@@ -57,7 +57,7 @@ class PPOClassicControlPreset(ParallelPreset):
         value_loss_scaling (float): Coefficient for the value function loss.
         clip_initial (float): Value for epsilon in the clipped PPO objective function at the beginning of training.
         clip_final (float): Value for epsilon in the clipped PPO objective function at the end of training.
-        epochs (int): Number of times to iterature through each batch.
+        epochs (int): Number of times to literature through each batch.
         minibatches (int): The number of minibatches to split each batch into.
         n_envs (int): Number of parallel actors.
         n_steps (int): Length of each rollout.

all/presets/classic_control/rainbow.py

@@ -72,7 +72,7 @@ class RainbowClassicControlPreset(Preset):
         atoms (int): The number of atoms in the categorical distribution used to represent
             the distributional value function.
         v_min (int): The expected return corresponding to the smallest atom.
-        v_max (int): The expected return correspodning to the larget atom.
+        v_max (int): The expected return corresponding to the largest atom.
         sigma (float): Initial noisy network noise.
         model_constructor (function): The function used to construct the neural model.
     """

all/presets/continuous/ppo.py

@@ -57,7 +57,7 @@ class PPOContinuousPreset(ParallelPreset):
         # is no greater than this bound. Set to 0 to disable.
         clip_initial (float): Value for epsilon in the clipped PPO objective function at the beginning of training.
         clip_final (float): Value for epsilon in the clipped PPO objective function at the end of training.
-        epochs (int): Number of times to iterature through each batch.
+        epochs (int): Number of times to literature through each batch.
         minibatches (int): The number of minibatches to split each batch into.
         n_envs (int): Number of parallel actors.
         n_steps (int): Length of each rollout.

all/presets/preset.py

@@ -6,7 +6,7 @@ class Preset(ABC):
     """
     A Preset Agent factory.
 
-    This class allows the user to instansiate preconfigured Agents and test Agents.
+    This class allows the user to instantiate preconfigured Agents and test Agents.
     All Agents constructed by the Preset share a network model and parameters.
     However, other objects, such as ReplayBuffers, are independently created for each Agent.
     The Preset can be saved and loaded from disk.
@@ -20,14 +20,14 @@ def __init__(self, name, device, hyperparameters):
     @abstractmethod
     def agent(self, writer=None, train_steps=float('inf')):
         """
-        Instansiate a training-mode Agent with the existing model.
+        Instantiate a training-mode Agent with the existing model.
 
         Args:
             writer (all.logging.Writer, optional): Coefficient for the entropy term in the total loss.
             train_steps (int, optional): The number of steps for which the agent will be trained.
 
         Returns:
-            all.agents.Agent: The instansiated Agent.
+            all.agents.Agent: The instantiated Agent.
         """
         pass
 
@@ -37,7 +37,7 @@ def test_agent(self):
         Instansiate a test-mode Agent with the existing model.
 
         Returns:
-            all.agents.Agent: The instansiated test Agent.
+            all.agents.Agent: The instantiated test Agent.
         """
         pass
 
@@ -46,7 +46,7 @@ def save(self, filename):
         Save the preset and the contained model to disk.
 
         The preset can later be loaded using torch.load(filename), allowing
-        a test mode agent to be instansiated for evaluation or other purposes.
+        a test mode agent to be instantiated for evaluation or other purposes.
 
         Args:
             filename (str): The path where the preset should be saved.
@@ -59,7 +59,7 @@ class ParallelPreset():
     A Preset ParallelAgent factory.
 
     This is the ParallelAgent version of all.presets.Preset.
-    This class allows the user to instansiate preconfigured ParallelAgents and test Agents.
+    This class allows the user to instantiate preconfigured ParallelAgents and test Agents.
     All Agents constructed by the ParallelPreset share a network model and parameters.
     However, other objects, such as ReplayBuffers, are independently created for each Agent.
     The ParallelPreset can be saved and loaded from disk.
@@ -73,24 +73,24 @@ def __init__(self, name, device, hyperparameters):
     @abstractmethod
     def agent(self, writer=None, train_steps=float('inf')):
         """
-        Instansiate a training-mode ParallelAgent with the existing model.
+        Instantiate a training-mode ParallelAgent with the existing model.
 
         Args:
             writer (all.logging.Writer, optional): Coefficient for the entropy term in the total loss.
             train_steps (int, optional): The number of steps for which the agent will be trained.
 
         Returns:
-            all.agents.ParallelAgent: The instansiated Agent.
+            all.agents.ParallelAgent: The instantiated Agent.
         """
         pass
 
     @abstractmethod
     def test_agent(self):
         """
-        Instansiate a test-mode Agent with the existing model.
+        Instantiate a test-mode Agent with the existing model.
 
         Returns:
-            all.agents.Agent: The instansiated test Agent.
+            all.agents.Agent: The instantiated test Agent.
         """
         pass
 
@@ -103,7 +103,7 @@ def save(self, filename):
         Save the preset and the contained model to disk.
 
         The preset can later be loaded using torch.load(filename), allowing
-        a test mode agent to be instansiated for evaluation or other purposes.
+        a test mode agent to be instantiated for evaluation or other purposes.
 
         Args:
             filename (str): The path where the preset should be saved.