File size: 1,971 Bytes
7155cf2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# Copyright 2024 Bytedance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
The base class for Actor
"""
from abc import ABC, abstractmethod
from typing import Any, Dict
import torch
from ...protocol import DataProto
from .config import ActorConfig
__all__ = ["BasePPOActor"]
class BasePPOActor(ABC):
def __init__(self, config: ActorConfig):
"""The base class for PPO actor
Args:
config (ActorConfig): a config passed to the PPOActor.
"""
self.config = config
@abstractmethod
def compute_log_prob(self, data: DataProto) -> torch.Tensor:
"""Compute logits given a batch of data.
Args:
data (DataProto): a batch of data represented by DataProto. It must contain key ```input_ids```,
```attention_mask``` and ```position_ids```.
Returns:
DataProto: a DataProto containing the key ```log_probs```
"""
pass
@abstractmethod
def update_policy(self, data: DataProto) -> Dict[str, Any]:
"""Update the policy with an iterator of DataProto
Args:
data (DataProto): an iterator over the DataProto that returns by
```make_minibatch_iterator```
Returns:
Dict: a dictionary contains anything. Typically, it contains the statistics during updating the model
such as ```loss```, ```grad_norm```, etc,.
"""
pass
|