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

by ShangtongZhang Python Version: v1.4 License: MIT

X-Ray Key Features Code Snippets(3)Community Discussions(1)Vulnerabilities Install Support

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.

Support

Quality

Security

License

Reuse

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

Quality

DeepRL has 0 bugs and 0 code smells.

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.

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.

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

Jupyter Notebook

Lines of Code : 53

License : Non-SPDX (NOASSERTION)

Copy

	- **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

Fast_rl

Jupyter Notebook

Lines of Code : 37

License : Permissive (Apache-2.0)

Copy

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

DeepRL,Evaluator

Python

Lines of Code : 25

License : No License

Copy

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

Trending Discussions on DeepRL

DRQN - Prefix tensor must be either a scalar or vector, but saw tensor

QUESTION

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:

...

ANSWER

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.

Source https://stackoverflow.com/questions/44961181

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

Vulnerabilities

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.

Support

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: