GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → chagmgang → distributed_reinforcement_learning

chagmgang / distributed_reinforcement_learning

Licence: other
implementation of distributed reinforcement learning with distributed tensorflow

Programming Languages

python
139335 projects - #7 most used programming language
Dockerfile
14818 projects

Labels

reinforcement-learningtensorflowimpalaapexr2d2distributed-tensorflowdistributed-reinforcement-learningscalable-reinforcement-learningdistributed-rl

Projects that are alternatives of or similar to distributed reinforcement learning

fast-sfdc
A VSCode plugin to develop Salesforce projects in vscode
Stars: ✭ 16 (-66.67%)
Mutual labels:  apex
ansible-cloudera-hadoop
ansible playbook to deploy cloudera hadoop components to the cluster
Stars: ✭ 51 (+6.25%)
Mutual labels:  impala
Script.apex
Evaluate Javascript expressions in Apex
Stars: ✭ 18 (-62.5%)
Mutual labels:  apex
apex-utils
Utility classes for Salesforce Apex development
Stars: ✭ 20 (-58.33%)
Mutual labels:  apex
apexmock
force.com Mock data and fixtures for Apex Unit Tests
Stars: ✭ 24 (-50%)
Mutual labels:  apex
docker-apex-stack
Utility scripts for creating an Oracle Application Express stack as a Docker container.
Stars: ✭ 67 (+39.58%)
Mutual labels:  apex
APEX-Q
A promise library for Salesforce
Stars: ✭ 30 (-37.5%)
Mutual labels:  apex
json2apex
Generate strongly typed apex code from a json structure.
Stars: ✭ 121 (+152.08%)
Mutual labels:  apex
apex
ANSI POSIX Environment neXt for Harvey OS
Stars: ✭ 25 (-47.92%)
Mutual labels:  apex
Addax
Addax is an open source universal ETL tool that supports most of those RDBMS and NoSQLs on the planet, helping you transfer data from any one place to another.
Stars: ✭ 615 (+1181.25%)
Mutual labels:  impala
SupervisedDepthPrediction
Pytorch framework for supervised depth prediction
Stars: ✭ 36 (-25%)
Mutual labels:  apex
apex-fp
Functional programming for Salesforce Apex
Stars: ✭ 231 (+381.25%)
Mutual labels:  apex
NebulaFramework
A development framework for Salesforce's Apex language & the Force.com platform
Stars: ✭ 28 (-41.67%)
Mutual labels:  apex
apex-query-builder
Convenient query builder for dynamic SOQL queries
Stars: ✭ 37 (-22.92%)
Mutual labels:  apex
incubator-linkis
Linkis helps easily connect to various back-end computation/storage engines(Spark, Python, TiDB...), exposes various interfaces(REST, JDBC, Java ...), with multi-tenancy, high performance, and resource control.
Stars: ✭ 2,459 (+5022.92%)
Mutual labels:  impala
ApexTriggerHandler
Another library implements Apex trigger handler design pattern.
Stars: ✭ 40 (-16.67%)
Mutual labels:  apex
hadoop-data-ingestion-tool
OLAP and ETL of Big Data
Stars: ✭ 17 (-64.58%)
Mutual labels:  impala
kapture-localization
Provide mapping and localization pipelines based on kapture format
Stars: ✭ 111 (+131.25%)
Mutual labels:  r2d2
amoss
Amoss - Apex Mock Objects, Spies and Stubs - A Simple Mocking framework for Apex (Salesforce)
Stars: ✭ 55 (+14.58%)
Mutual labels:  apex
xingtian
xingtian is a componentized library for the development and verification of reinforcement learning algorithms
Stars: ✭ 229 (+377.08%)
Mutual labels:  impala
View All Similar Projects ➔

Implementation of Distributed Reinforcement Learning with Tensorflow

Information

  • 20 actors with 1 learner.
  • Tensorflow implementation with distributed tensorflow of server-client architecture.
  • Recurrent Experience Replay in Distributed Reinforcement Learning is implemented in Breakout-Deterministic-v4 with POMDP(Observation not provided with 20% probability)

Dependency

opencv-python
gym[atari]
tensorboardX
tensorflow==1.14.0

Implementation

How to Run

  • A3C: Asynchronous Methods for Deep Reinforcement Learning
CUDA_VISIBLE_DEVICES=-1 python train_a3c.py --job_name --job_name actor --task 0

CUDA_VISIBLE_DEVICES=-1 python train_a3c.py --job_name --job_name actor --task 0
CUDA_VISIBLE_DEVICES=-1 python train_a3c.py --job_name --job_name actor --task 1
CUDA_VISIBLE_DEVICES=-1 python train_a3c.py --job_name --job_name actor --task 2
...
CUDA_VISIBLE_DEVICES=-1 python train_a3c.py --job_name --job_name actor --task 19
  • Ape-x: DISTRIBUTED PRIORITIZED EXPERIENCE REPLAY
python train_apex.py --job_name learner --task 0

CUDA_VISIBLE_DEVICES=-1 python train_apex.py --job_name actor --task 0
CUDA_VISIBLE_DEVICES=-1 python train_apex.py --job_name actor --task 1
CUDA_VISIBLE_DEVICES=-1 python train_apex.py --job_name actor --task 2
...
CUDA_VISIBLE_DEVICES=-1 python train_apex.py --job_name actor --task 19
  • IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
python train_impala.py --job_name learner --task 0

CUDA_VISIBLE_DEVICES=-1 python train_impala.py --job_name actor --task 0
CUDA_VISIBLE_DEVICES=-1 python train_impala.py --job_name actor --task 1
CUDA_VISIBLE_DEVICES=-1 python train_impala.py --job_name actor --task 2
...
CUDA_VISIBLE_DEVICES=-1 python train_impala.py --job_name actor --task 19
  • R2D2: Recurrent Experience Replay in Distributed Reinforcement Learning
python train_r2d2.py --job_name learner --task 0

CUDA_VISIBLE_DEVICES=-1 python train_r2d2.py --job_name actor --task 0
CUDA_VISIBLE_DEVICES=-1 python train_r2d2.py --job_name actor --task 1
CUDA_VISIBLE_DEVICES=-1 python train_r2d2.py --job_name actor --task 2
...
CUDA_VISIBLE_DEVICES=-1 python train_r2d2.py --job_name actor --task 39

Reference

  1. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
  2. DISTRIBUTED PRIORITIZED EXPERIENCE REPLAY
  3. Recurrent Experience Replay in Distributed Reinforcement Learning
  4. deepmind/scalable_agent
  5. google-research/seed-rl
  6. Asynchronous_Advatnage_Actor_Critic
  7. Relational_Deep_Reinforcement_Learning
  8. Deep Recurrent Q-Learning for Partially Observable MDPs
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].