Tianshou/test/highlevel/env_factory.py

from tianshou.highlevel.env import (
    EnvFactoryGymnasium,
    VectorEnvType,
)


class DiscreteTestEnvFactory(EnvFactoryGymnasium):
    def __init__(self):
        super().__init__(task="CartPole-v0", seed=42, venv_type=VectorEnvType.DUMMY)


class ContinuousTestEnvFactory(EnvFactoryGymnasium):
    def __init__(self):
        super().__init__(task="Pendulum-v1", seed=42, venv_type=VectorEnvType.DUMMY)
Add some basic tests for high-level experiment builder API 2023-10-05 19:22:04 +02:00			`from tianshou.highlevel.env import (`
Improve environment factory abstractions in high-level API: * EnvFactory now uses the creation of a single environment as the basic functionality which the more high-level functions build upon * Introduce enum EnvMode to indicate the purpose for which an env is created, allowing the factory creation process to change its behaviour accordingly * Add EnvFactoryGymnasium to provide direct support for envs that can be created via gymnasium.make - EnvPool is supported via an injectible EnvPoolFactory - Existing EnvFactory implementations are now derived from EnvFactoryGymnasium * Use a separate environment (which uses new EnvMode.WATCH) for watching agent performance after training (instead of using test environments, which the user may want to configure differently) 2024-01-10 15:37:58 +01:00			`EnvFactoryGymnasium,`
			`VectorEnvType,`
Add some basic tests for high-level experiment builder API 2023-10-05 19:22:04 +02:00			`)`


Improve environment factory abstractions in high-level API: * EnvFactory now uses the creation of a single environment as the basic functionality which the more high-level functions build upon * Introduce enum EnvMode to indicate the purpose for which an env is created, allowing the factory creation process to change its behaviour accordingly * Add EnvFactoryGymnasium to provide direct support for envs that can be created via gymnasium.make - EnvPool is supported via an injectible EnvPoolFactory - Existing EnvFactory implementations are now derived from EnvFactoryGymnasium * Use a separate environment (which uses new EnvMode.WATCH) for watching agent performance after training (instead of using test environments, which the user may want to configure differently) 2024-01-10 15:37:58 +01:00			`class DiscreteTestEnvFactory(EnvFactoryGymnasium):`
			`def __init__(self):`
			`super().__init__(task="CartPole-v0", seed=42, venv_type=VectorEnvType.DUMMY)`
Add some basic tests for high-level experiment builder API 2023-10-05 19:22:04 +02:00

Improve environment factory abstractions in high-level API: * EnvFactory now uses the creation of a single environment as the basic functionality which the more high-level functions build upon * Introduce enum EnvMode to indicate the purpose for which an env is created, allowing the factory creation process to change its behaviour accordingly * Add EnvFactoryGymnasium to provide direct support for envs that can be created via gymnasium.make - EnvPool is supported via an injectible EnvPoolFactory - Existing EnvFactory implementations are now derived from EnvFactoryGymnasium * Use a separate environment (which uses new EnvMode.WATCH) for watching agent performance after training (instead of using test environments, which the user may want to configure differently) 2024-01-10 15:37:58 +01:00			`class ContinuousTestEnvFactory(EnvFactoryGymnasium):`
			`def __init__(self):`
			`super().__init__(task="Pendulum-v1", seed=42, venv_type=VectorEnvType.DUMMY)`