DeepRL | Modularized Implementation of Deep RL Algorithms in PyTorch | Reinforcement Learning library

 by   ShangtongZhang Python Version: v1.4 License: MIT

kandi X-RAY | DeepRL Summary

kandi X-RAY | DeepRL Summary

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

If you have any question or want to report a bug, please open an issue instead of emailing me directly. Modularized implementation of popular deep RL algorithms in PyTorch. Easy switch between toy tasks and challenging games. The DQN agent, as well as C51 and QR-DQN, has an asynchronous actor for data generation and an asynchronous replay buffer for transferring data to GPU. Using 1 RTX 2080 Ti and 3 threads, the DQN agent runs for 10M steps (40M frames, 2.5M gradient updates) for Breakout within 6 hours.

            kandi-support Support

              DeepRL has a medium active ecosystem.
              It has 2938 star(s) with 658 fork(s). There are 92 watchers for this library.
              It had no major release in the last 12 months.
              There are 5 open issues and 86 have been closed. On average issues are closed in 26 days. There are 1 open pull requests and 0 closed requests.
              It has a neutral sentiment in the developer community.
              The latest version of DeepRL is v1.4

            kandi-Quality Quality

              DeepRL has 0 bugs and 0 code smells.

            kandi-Security Security

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

            kandi-License License

              DeepRL 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

              DeepRL releases are available to install and integrate.
              Build file is available. You can build the component from source.
              Installation instructions are not available. Examples and code snippets are available.
              DeepRL saves you 1155 person hours of effort in developing the same functionality from scratch.
              It has 2608 lines of code, 244 functions and 32 files.
              It has medium code complexity. Code complexity directly impacts maintainability of the code.

            Top functions reviewed by kandi - BETA

            kandi has reviewed DeepRL and discovered the below as its top functions. This is intended to give you an instant insight into DeepRL implemented functionality, and help decide if they suit your requirements.
            • Plots ANOVA
            • Load results from files
            • Plot games
            • Returns all log directories that match the pattern
            • Run jujoco
            • Merges a configuration dictionary
            • Compute the loss function
            • Convert input to tensor
            • Perform the transition
            • Greedy greedy implementation
            • Get a logger
            • Select the best matching parameters
            • Forward function to the function
            • Generate a tag
            • Calculate the objective function
            • Forward action function
            • Records an episode
            • Main loop
            • Command line interface for batchatari
            • Plot DDP 3D example
            • Creates a random environment
            • Reduce a set of patterns to a given score function
            • Plots PPO
            • Reduce all tfevents under the given root directory
            • Compute the loss
            • Run the agent
            Get all kandi verified functions for this library.

            DeepRL Key Features

            No Key Features are available at this moment for DeepRL.

            DeepRL Examples and Code Snippets

            copy iconCopy
            	- **Cognitive AI** , powered by Deep Neural networks, such as 
            		- Computer vision, 
            		- Natural Language Proessing, Understanding,  Generataion (NLP-NLU-NLG), 				
            		- Audio & Speech analytics, 
            		- Conversational AI,
            		- Multimodal analytics
            Jupyter Notebookdot img2Lines of Code : 37dot img2License : Permissive (Apache-2.0)
            copy iconCopy
            from fast_rl.agents.dqn import create_dqn_model, dqn_learner
            from fast_rl.agents.dqn_models import *
            from fast_rl.core.agent_core import ExperienceReplay,  GreedyEpsilon
            from fast_rl.core.data_block import MDPDataBunch
            from fast_rl.core.metrics impor  
            Pythondot img3Lines of Code : 25dot img3no licencesLicense : No License
            copy iconCopy
            import gym 
            import dm_control2gym
            from algorithms import PPO, TRPO, SAC, CGP, TD3
            from evaluator import Evaluator
            from evaluator.plot import plot_learning_curves, load_dataset
            envs = [
                ('cartpole', 'balance'),
                ('cartpole', 'swingup'),

            Community Discussions


            DRQN - Prefix tensor must be either a scalar or vector, but saw tensor
            Asked 2017-Jul-25 at 02:51

            In following this tutorial, I am receiving the following error:

            ValueError: prefix tensor must be either a scalar or vector, but saw tensor: Tensor("Placeholder_2:0", dtype=int32)

            The error originates from these lines:



            Answered 2017-Jul-24 at 01:52

            I met the same problem with the version of tensorflow is 1.2.+.

            When i changed it to 1.1.0, the problem resolved.

            I think it because the API of rnn_cell.zero_state makes arg batch_size must be a scalar or vector, but not tensor.

            So, if you change batch_size to scalar, e.g. 128, the problem also could be resolved.


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


            No vulnerabilities reported

            Install DeepRL

            You can download it from GitHub.
            You can use DeepRL like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.


            For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .
            Find more information at:

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

            Find more libraries

            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 ShangtongZhang


            by ShangtongZhangPython


            by ShangtongZhangPython


            by ShangtongZhangPython


            by ShangtongZhangPython