openrl.rewards package¶ Submodules¶ openrl.rewards.base_reward module¶ class openrl.rewards.base_reward.BaseReward(env: openrl.envs.vec_env.base_venv.BaseVecEnv)[source]¶ Bases: object batch_rewards(buffer: Any) → Dict[str, Any][source]¶ step_reward(data: Dict[str, Any]) → Union[numpy.ndarray, List[Dict[str, Any]]][source]¶ openrl.rewards.gail_reward module¶ class openrl.rewards.gail_reward.GAILReward(env: openrl.envs.vec_env.base_venv.BaseVecEnv)[source]¶ Bases: openrl.rewards.base_reward.BaseReward set_discriminator(cfg, discriminator: torch.nn.modules.module.Module)[source]¶ step_reward(data: Dict[str, Any]) → Tuple[numpy.ndarray, List[Dict[str, Any]]][source]¶ class openrl.rewards.gail_reward.RewardPredictor(cfg, discriminator: torch.nn.modules.module.Module)[source]¶ Bases: object openrl.rewards.nlp_reward module¶ Module contents¶ class openrl.rewards.RewardFactory[source]¶ Bases: object static auto_register(reward_class: Any)[source]¶ static get_reward_class(reward_class: Any, env: openrl.envs.vec_env.base_venv.BaseVecEnv)[source]¶ static register(reward_name, reward_class)[source]¶