evolearn.environments module¶
-
class
evolearn.environments.environment_gym.
BalancingPole
[source]¶ FlappyBird test class
Parameters: genome (NaN) – population of cppn networks.
-
class
evolearn.environments.environment_gym.
FlappyBird
[source]¶ FlappyBird test class
Parameters: genome (NaN) – population of cppn networks.
-
class
evolearn.environments.environment_simple.
Recognition
[source]¶ General image recognition object.
-
class
evolearn.environments.environment_simple.
SimpleEnvironment
[source]¶ Simple wrapped callable nutrient environment.
- Todo:
- Allow for the import of txt file for defining maze/track boundaries.
- Connect imported boundaries to evaluation loop break collision flag.
-
build_actions
()[source]¶ Builds an accessible dictionary of possible actions to be called with each agent action to provide adjustments for location and heading adjustments.
Returns: environment action dict. Indices define position and heading adjustments for a selected action.
-
collision_check
()[source]¶ Collision check to potentially break current agent’s evaluation.
Returns: collide Boolean
-
reformat_action
(agent_output)[source]¶ Reformat raw network output into environment-specific (or experiment specified) action/class choice.
Returns: reformatted action/class index
-
return_reward
()[source]¶ Returns reward for agent’s current location.
Returns: reward/state at agent.location