def run_metalearner_rnd_model(config, i): env = gym.make('MountainCarContinuous-v0') state_dim = env.observation_space.shape[0] action_dim = env.action_space.shape[0] experiment = ExperimentDDPG('MountainCarContinuous-v0', env, config) agent = DDPGBulletMetaCriticRNDModelAgent(state_dim, action_dim, config) experiment.run_metalearner_rnd_model(agent, i) env.close()
def run_metalearner_rnd_model(env_name, config, trial): env = create_env(env_name) state_dim = env.observation_space.shape action_dim = env.action_space.shape[0] experiment = ExperimentDDPG(env_name, env, config) agent = DDPGAerisMetaCriticRNDModelAgent(state_dim, action_dim, config) experiment.run_metalearner_rnd_model(agent, trial) env.close()