def __init__(self, env: gym.Env):
self.env = utils.torchenv(env)
self.ep_rewards: List[float] = []
self.actor_optimizer = Adam([])
self.critic_optimizer = Adam([])
self.replay: Replay = NoReplay(1)
def __init__(self, env: gym.Env):
self.env = utils.torchenv(env)
self.ep_rewards = []
self.replay = None
self.optimizer = None
self.target_dqn = None
def __init__(self, env: gym.Env):
self.env = utils.torchenv(env)
self.ep_rewards: List[float] = []
self.avg_reward = 0.0
self.optimizer: Optimizer = Adam([])
self.replay: Replay = NoReplay(1)
def __init__(self, env: gym.Env):
self.env = utils.torchenv(env)
self.ep_rewards = []
self.replay = None
self.critic_optimizer = None
self.actor_optimizer = None
self.target_critics = None