tianshou | An elegant PyTorch deep reinforcement | Reinforcement Learning library

 by   thu-ml Python Version: 0.5.1 License: MIT

kandi X-RAY | tianshou Summary

kandi X-RAY | tianshou Summary

tianshou is a Python library typically used in Artificial Intelligence, Reinforcement Learning, Deep Learning, Pytorch applications. tianshou has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can install using 'pip install tianshou' or download it from GitHub, PyPI.

Tianshou (天授) is a reinforcement learning platform based on pure PyTorch. Unlike existing reinforcement learning libraries, which are mainly based on TensorFlow, have many nested classes, unfriendly API, or slow-speed, Tianshou provides a fast-speed modularized framework and pythonic API for building the deep reinforcement learning agent with the least number of lines of code. The supported interface algorithms currently include:.

            kandi-support Support

              tianshou has a medium active ecosystem.
              It has 6356 star(s) with 988 fork(s). There are 84 watchers for this library.
              There were 1 major release(s) in the last 6 months.
              There are 55 open issues and 494 have been closed. On average issues are closed in 43 days. There are 5 open pull requests and 0 closed requests.
              It has a neutral sentiment in the developer community.
              The latest version of tianshou is 0.5.1

            kandi-Quality Quality

              tianshou has 0 bugs and 0 code smells.

            kandi-Security Security

              tianshou has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.
              tianshou code analysis shows 0 unresolved vulnerabilities.
              There are 0 security hotspots that need review.

            kandi-License License

              tianshou is licensed under the MIT License. This license is Permissive.
              Permissive licenses have the least restrictions, and you can use them in most projects.

            kandi-Reuse Reuse

              tianshou releases are available to install and integrate.
              Deployable package is available in PyPI.
              Build file is available. You can build the component from source.
              Installation instructions, examples and code snippets are available.

            Top functions reviewed by kandi - BETA

            kandi has reviewed tianshou and discovered the below as its top functions. This is intended to give you an instant insight into tianshou implemented functionality, and help decide if they suit your requirements.
            • Test the Poisson model
            • Creates a deep Forest environment
            • Make anari environment
            • Seed workers
            • Test the experiment
            • Add a batch to the model
            • Returns True if this batch is empty
            • Add new index
            • Perform a test
            • Test the discrete CRR
            • Test the redq function
            • Train the model
            • Test the discrete bqq
            • Runs the test suite
            • Test the trpo model
            • Test the test suite
            • Test QRDQN
            • Creates a Forest model
            • Evaluate a discrete discretization
            • Test the FQF function
            • Runs test suite
            • Test the DQN
            • Run a test suite
            • Test the C51 network
            • Test T3 B3
            • Test A2C
            Get all kandi verified functions for this library.

            tianshou Key Features

            No Key Features are available at this moment for tianshou.

            tianshou Examples and Code Snippets

            Citing Tianshou
            pypidot img1Lines of Code : 6dot img1no licencesLicense : No License
            copy iconCopy
              title={Tianshou: A Highly Modularized Deep Reinforcement Learning Library},
              author={Weng, Jiayi and Chen, Huayu and Yan, Dong and You, Kaichao and Duburcq, Alexis and Zhang, Minghao and Su, Yi and Su, Hang and Zhu, Jun},
            pypidot img2Lines of Code : 5dot img2no licencesLicense : No License
            copy iconCopy
            $ pip install tianshou
            $ conda install -c conda-forge tianshou
            $ pip install git+https://github.com/thu-ml/tianshou.git@master --upgrade
            import tianshou
            Pythondot img3Lines of Code : 0dot img3License : Permissive (MIT)
            copy iconCopy
            EnvWrapper is the complete capsulation of the simulated environment. It receives actions from outside (policy/strategy/agent), simulates the changes in the market, and then replies rewards and updated states, thus forming an interaction loop.
            In Qli  
            tianshou - plotter
            Pythondot img4Lines of Code : 261dot img4License : Permissive (MIT License)
            copy iconCopy
            #!/usr/bin/env python3
            import argparse
            import os
            import re
            import matplotlib.pyplot as plt
            import matplotlib.ticker as mticker
            import numpy as np
            from tools import csv2numpy, find_all_files, group_files
            def smooth(y, radius, mode='two_sided', val  
            tianshou - atari ppo
            Pythondot img5Lines of Code : 254dot img5License : Permissive (MIT License)
            copy iconCopy
            import argparse
            import datetime
            import os
            import pprint
            import numpy as np
            import torch
            from atari_network import DQN, layer_init, scale_obs
            from atari_wrapper import make_atari_env
            from torch.optim.lr_scheduler import LambdaLR
            from torch.utils.tens  
            tianshou - vizdoom ppo
            Pythondot img6Lines of Code : 246dot img6License : Permissive (MIT License)
            copy iconCopy
            import argparse
            import datetime
            import os
            import pprint
            import numpy as np
            import torch
            from env import make_vizdoom_env
            from network import DQN
            from torch.optim.lr_scheduler import LambdaLR
            from torch.utils.tensorboard import SummaryWriter
            from ti  

            Community Discussions


            Keras: AttributeError: 'Adam' object has no attribute '_name'
            Asked 2022-Apr-16 at 15:05

            I want to compile my DQN Agent but I get error: AttributeError: 'Adam' object has no attribute '_name',



            Answered 2022-Apr-16 at 15:05

            Your error came from importing Adam with from keras.optimizer_v1 import Adam, You can solve your problem with tf.keras.optimizers.Adam from TensorFlow >= v2 like below:

            (The lr argument is deprecated, it's better to use learning_rate instead.)

            Source https://stackoverflow.com/questions/71894769


            What are vectorized environments in reinforcement learning?
            Asked 2022-Mar-25 at 10:37

            I'm having a hard time wrapping my head around what and when vectorized environments should be used. If you can provide an example of a use case, that would be great.

            Documentation of vectorized environments in SB3: https://stable-baselines3.readthedocs.io/en/master/guide/vec_envs.html



            Answered 2022-Mar-25 at 10:37

            Vectorized Environments are a method for stacking multiple independent environments into a single environment. Instead of executing and training an agent on 1 environment per step, it allows to train the agent on multiple environments per step.

            Usually you also want these environment to have different seeds, in order to gain more diverse experience. This is very useful to speed up training.

            I think they are called "vectorized" since each training step the agent observes multiple states (inserted in a vector), outputs multiple actions (one for each environment), which are inserted in a vector, and receives multiple rewards. Hence the "vectorized" term

            Source https://stackoverflow.com/questions/71549439


            How does a gradient backpropagates through random samples?
            Asked 2022-Mar-25 at 03:06

            I'm learning about policy gradients and I'm having hard time understanding how does the gradient passes through a random operation. From here: It is not possible to directly backpropagate through random samples. However, there are two main methods for creating surrogate functions that can be backpropagated through.

            They have an example of the score function:



            Answered 2021-Nov-30 at 05:48

            It is indeed true that sampling is not a differentiable operation per se. However, there exist two (broad) ways to mitigate this - [1] The REINFORCE way and [2] The reparameterization way. Since your example is related to [1], I will stick my answer to REINFORCE.

            What REINFORCE does is it entirely gets rid of sampling operation in the computation graph. However, the sampling operation remains outside the graph. So, your statement

            .. how does the gradient passes through a random operation ..

            isn't correct. It does not pass through any random operation. Let's see your example

            Source https://stackoverflow.com/questions/70163823


            Relationship of Horizon and Discount factor in Reinforcement Learning
            Asked 2022-Mar-13 at 17:50

            What is the connection between discount factor gamma and horizon in RL.

            What I have learned so far is that the horizon is the agent`s time to live. Intuitively, agents with finite horizon will choose actions differently than if it has to live forever. In the latter case, the agent will try to maximize all the expected rewards it may get far in the future.

            But the idea of the discount factor is also the same. Are the values of gamma near zero makes the horizon finite?



            Answered 2022-Mar-13 at 17:50

            Horizon refers to how many steps into the future the agent cares about the reward it can receive, which is a little different from the agent's time to live. In general, you could potentially define any arbitrary horizon you want as the objective. You could define a 10 step horizon, in which the agent makes a decision that will enable it to maximize the reward it will receive in the next 10 time steps. Or we could choose a 100, or 1000, or n step horizon!

            Usually, the n-step horizon is defined using n = 1 / (1-gamma). Therefore, 10 step horizon will be achieved using gamma = 0.9, while 100 step horizon can be achieved with gamma = 0.99

            Therefore, any value of gamma less than 1 imply that the horizon is finite.

            Source https://stackoverflow.com/questions/71459191


            OpenAI-Gym and Keras-RL: DQN expects a model that has one dimension for each action
            Asked 2022-Mar-02 at 10:55

            I am trying to set a Deep-Q-Learning agent with a custom environment in OpenAI Gym. I have 4 continuous state variables with individual limits and 3 integer action variables with individual limits.

            Here is the code:



            Answered 2021-Dec-23 at 11:19

            As we talked about in the comments, it seems that the Keras-rl library is no longer supported (the last update in the repository was in 2019), so it's possible that everything is inside Keras now. I take a look at Keras documentation and there are no high-level functions to build a reinforcement learning model, but is possible to use lower-level functions to this.

            • Here is an example of how to use Deep Q-Learning with Keras: link

            Another solution may be to downgrade to Tensorflow 1.0 as it seems the compatibility problem occurs due to some changes in version 2.0. I didn't test, but maybe the Keras-rl + Tensorflow 1.0 may work.

            There is also a branch of Keras-rl to support Tensorflow 2.0, the repository is archived, but there is a chance that it will work for you

            Source https://stackoverflow.com/questions/70261352


            gym package not identifying ten-armed-bandits-v0 env
            Asked 2022-Feb-08 at 08:01


            • Python: 3.9
            • OS: Windows 10

            When I try to create the ten armed bandits environment using the following code the error is thrown not sure of the reason.



            Answered 2022-Feb-08 at 08:01

            It could be a problem with your Python version: k-armed-bandits library was made 4 years ago, when Python 3.9 didn't exist. Besides this, the configuration files in the repo indicates that the Python version is 2.7 (not 3.9).

            If you create an environment with Python 2.7 and follow the setup instructions it works correctly on Windows:

            Source https://stackoverflow.com/questions/70858340


            ValueError: Input 0 of layer "max_pooling2d" is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: (None, 3, 51, 39, 32)
            Asked 2022-Feb-01 at 07:31

            I have two different problems occurs at the same time.

            I am having dimensionality problems with MaxPooling2d and having same dimensionality problem with DQNAgent.

            The thing is, I can fix them seperately but cannot at the same time.

            First Problem

            I am trying to build a CNN network with several layers. After I build my model, when I try to run it, it gives me an error.



            Answered 2022-Feb-01 at 07:31

            Issue is with input_shape. input_shape=input_shape[1:]

            Working sample code

            Source https://stackoverflow.com/questions/70808035


            Stablebaselines3 logging reward with custom gym
            Asked 2021-Dec-25 at 01:10

            I have this custom callback to log the reward in my custom vectorized environment, but the reward appears in console as always [0] and is not logged in tensorboard at all



            Answered 2021-Dec-25 at 01:10

            You need to add [0] as indexing,

            so where you wrote self.logger.record('reward', self.training_env.get_attr('total_reward')) you just need to index with self.logger.record('reward', self.training_env.get_attr ('total_reward')[0])

            Source https://stackoverflow.com/questions/70468394


            What is the purpose of [np.arange(0, self.batch_size), action] after the neural network?
            Asked 2021-Dec-23 at 11:07

            I followed a PyTorch tutorial to learn reinforcement learning(TRAIN A MARIO-PLAYING RL AGENT) but I am confused about the following code:



            Answered 2021-Dec-23 at 11:07

            Essentially, what happens here is that the output of the net is being sliced to get the desired part of the Q table.

            The (somewhat confusing) index of [np.arange(0, self.batch_size), action] indexes each axis. So, for axis with index 1, we pick the item indicated by action. For index 0, we pick all items between 0 and self.batch_size.

            If self.batch_size is the same as the length of dimension 0 of this array, then this slice can be simplified to [:, action] which is probably more familiar to most users.

            Source https://stackoverflow.com/questions/70458347


            DQN predicts same action value for every state (cart pole)
            Asked 2021-Dec-22 at 15:55

            I'm trying to implement a DQN. As a warm up I want to solve CartPole-v0 with a MLP consisting of two hidden layers along with input and output layers. The input is a 4 element array [cart position, cart velocity, pole angle, pole angular velocity] and output is an action value for each action (left or right). I am not exactly implementing a DQN from the "Playing Atari with DRL" paper (no frame stacking for inputs etc). I also made a few non standard choices like putting done and the target network prediction of action value in the experience replay, but those choices shouldn't affect learning.

            In any case I'm having a lot of trouble getting the thing to work. No matter how long I train the agent it keeps predicting a higher value for one action over another, for example Q(s, Right)> Q(s, Left) for all states s. Below is my learning code, my network definition, and some results I get from training



            Answered 2021-Dec-19 at 16:09

            There was nothing wrong with the network definition. It turns out the learning rate was too high and reducing it 0.00025 (as in the original Nature paper introducing the DQN) led to an agent which can solve CartPole-v0.

            That said, the learning algorithm was incorrect. In particular I was using the wrong target action-value predictions. Note the algorithm laid out above does not use the most recent version of the target network to make predictions. This leads to poor results as training progresses because the agent is learning based on stale target data. The way to fix this is to just put (s, a, r, s', done) into the replay memory and then make target predictions using the most up to date version of the target network when sampling a mini batch. See the code below for an updated learning loop.

            Source https://stackoverflow.com/questions/70382999

            Community Discussions, Code Snippets contain sources that include Stack Exchange Network


            No vulnerabilities reported

            Install tianshou

            Tianshou is currently hosted on PyPI and conda-forge. It requires Python >= 3.6.
            This is an example of Deep Q Network. You can also run the full script at test/discrete/test_dqn.py.


            The tutorials and API documentation are hosted on tianshou.readthedocs.io. The example scripts are under test/ folder and examples/ folder.
            Find more information at:

            Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items

            Find more libraries
          • PyPI

            pip install tianshou

          • CLONE
          • HTTPS


          • CLI

            gh repo clone thu-ml/tianshou

          • sshUrl


          • Stay Updated

            Subscribe to our newsletter for trending solutions and developer bootcamps

            Agree to Sign up and Terms & Conditions

            Share this Page

            share link

            Consider Popular Reinforcement Learning Libraries

            Try Top Libraries by thu-ml


            by thu-mlPython


            by thu-mlPython


            by thu-mlPython


            by thu-mlC++


            by thu-mlPython