iminders/tbase

This repo was moved to: https://github.com/tradingAI/tbase

tbase's Issues

windows anaconda Pytorch EOFError: Ran out of input when num_workers>0

https://discuss.pytorch.org/t/pytorch-windows-eoferror-ran-out-of-input-when-num-workers-0/25918

solved the issue by changing protocol=None in pythons multiprocessing/reduction.py to 4.

class ForkingPickler(pickle.Pickler):
    '''Pickler subclass used by multiprocessing.'''
    _extra_reducers = {}
    _copyreg_dispatch_table = copyreg.dispatch_table

    def __init__(self, *args):
        super().__init__(*args)
        self.dispatch_table = self._copyreg_dispatch_table.copy()
        self.dispatch_table.update(self._extra_reducers)

    @classmethod
    def register(cls, type, reduce):
        '''Register a reduce function for a type.'''
        cls._extra_reducers[type] = reduce

    @classmethod
    def dumps(cls, obj, protocol=4):
        buf = io.BytesIO()
        cls(buf, protocol).dump(obj)
        return buf.getbuffer()

    loads = pickle.loads

register = ForkingPickler.register

def dump(obj, file, protocol=4):
    '''Replacement for pickle.dump() using ForkingPickler.'''
    ForkingPickler(file, protocol).dump(obj)

Ubuntu GPU 环境下多进程运行时内存增长问题

系统环境

Ubuntu 18.04
GPU: GTX 1080
Memory: 8G

运行命令： python3 -m tbase.run --num_env 2

错误信息：
Traceback (most recent call last): File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/usr/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/ubuntu/gopath/src/github.com/iminders/tbase/tbase/run.py", line 56, in <module> main() File "/home/ubuntu/gopath/src/github.com/iminders/tbase/tbase/run.py", line 50, in main agent.learn() File "/home/ubuntu/gopath/src/github.com/iminders/tbase/tbase/agents/ddpg/agent.py", line 152, in learn sample_size=self.args.sample_size) File "/home/ubuntu/gopath/src/github.com/iminders/tbase/tbase/agents/ddpg/agent.py", line 63, in explore worker.start() File "/usr/lib/python3.6/multiprocessing/process.py", line 105, in start self._popen = self._Popen(self) File "/usr/lib/python3.6/multiprocessing/context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "/usr/lib/python3.6/multiprocessing/context.py", line 284, in _Popen return Popen(process_obj) File "/usr/lib/python3.6/multiprocessing/popen_spawn_posix.py", line 32, in __init__ super().__init__(process_obj) File "/usr/lib/python3.6/multiprocessing/popen_fork.py", line 19, in __init__ self._launch(process_obj) File "/usr/lib/python3.6/multiprocessing/popen_spawn_posix.py", line 59, in _launch cmd, self._fds) File "/usr/lib/python3.6/multiprocessing/util.py", line 417, in spawnv_passfds False, False, None) OSError: [Errno 12] Cannot allocate memory Segmentation fault (core dumped)

添加Model Graph到tensorboard中

portfolio抖动现象

可能的原因：当模型在最优解附近时，再使用梯度下降或其他的基于梯度的最优化方法求解时，很有可能直接跳过最优解，从而导致交易失败。
例如：000001.SZ(平安银行), 2020.02.27日最高价: 15.15, 最低价:14.89
如果模型这时的输出决策：15.15卖出，14.89买入，再往梯度方向调整，很有可能就会出现卖出价格过高，买进价格过低，无法达成交易，最终使收益率阶梯式下降

这种现象是否是合理？

增加一个BuyAndHold Agent 作为策略参考基准

增加一个BuyAndHold Agent 作为策略参考基准:

• 个股
• 指数

gpu支持

多进程gpu支持, 加带训练

相同的参数，由于随机过程导致的差异常大

1. 设置随机数种子，使模型训练可复现？
2. 由于撮合成交机制，微小的价格差异，导致行为差别非常大。微小的随机差异，可能使portfolio值相差非常大，容易形成非常剧烈的抖动现象， 如何避免这种情况？

这两种方法可行性探索，如果可行则更新到repo中 @iminders

build time out

docker-compose up timeout

liuwen@pro tbase % docker-compose up
Starting tbase_bazel_1 ... done
Attaching to tbase_bazel_1
bazel_1  | Loading:
bazel_1  | Loading: 0 packages loaded
bazel_1  | Loading: 0 packages loaded
bazel_1  | Analyzing: 7 targets (8 packages loaded, 0 targets configured)
bazel_1  | Analyzing: 7 targets (26 packages loaded, 100 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)

bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | Analyzing: 7 targets (28 packages loaded, 157 targets configured)
bazel_1  | INFO: Call stack for the definition of repository 'remotejdk11_linux' which is a http_archive (rule definition at /root/cache/bazel/c50f8f05fa35fa56205e52
507df67c8f/external/bazel_tools/tools/build_defs/repo/http.bzl:292:16):
bazel_1  |  - /root/cache/bazel/c50f8f05fa35fa56205e52507df67c8f/external/bazel_tools/tools/build_defs/repo/utils.bzl:205:9
bazel_1  |  - /root/cache/bazel/c50f8f05fa35fa56205e52507df67c8f/external/bazel_tools/tools/build_defs/repo/utils.bzl:205:9
bazel_1  |  - /DEFAULT.WORKSPACE.SUFFIX:216:1
bazel_1  | WARNING: Download from https://mirror.bazel.build/openjdk/azul-zulu11.2.3-jdk11.0.1/zulu11.2.3-jdk11.0.1-linux_x64.tar.gz failed: class javax.net.ssl.SSLP
rotocolException Read timed out
bazel_1  | ERROR: An error occurred during the fetch of repository 'remotejdk11_linux':
bazel_1  |    java.io.IOException: Error downloading [https://mirror.bazel.build/openjdk/azul-zulu11.2.3-jdk11.0.1/zulu11.2.3-jdk11.0.1-linux_x64.tar.gz] to /root/ca
che/bazel/c50f8f05fa35fa56205e52507df67c8f/external/remotejdk11_linux/zulu11.2.3-jdk11.0.1-linux_x64.tar.gz: Read timed out
bazel_1  | ERROR: /root/cache/bazel/c50f8f05fa35fa56205e52507df67c8f/external/bazel_tools/tools/jdk/BUILD:494:1: @bazel_tools//tools/jdk:remote_jdk11 depends on @rem
otejdk11_linux//:jdk in repository @remotejdk11_linux which failed to fetch. no such package '@remotejdk11_linux//': java.io.IOException: Error downloading [https://
mirror.bazel.build/openjdk/azul-zulu11.2.3-jdk11.0.1/zulu11.2.3-jdk11.0.1-linux_x64.tar.gz] to /root/cache/bazel/c50f8f05fa35fa56205e52507df67c8f/external/remotejdk1
1_linux/zulu11.2.3-jdk11.0.1-linux_x64.tar.gz: Read timed out
bazel_1  | ERROR: Analysis of target '//tbase/common:cmd_util_test' failed; build aborted: Analysis failed