Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / PKU-Alignment/omnisafe issues and pull requests

#365 - [Question] Multiple constraints with CPO

Issue - State: closed - Opened by adamelyoumi 10 days ago - 2 comments
Labels: question

#364 - [Question]

Issue - State: open - Opened by Eureka725 about 1 month ago - 1 comment
Labels: question

#363 - [Question] How to manage constraints?

Issue - State: closed - Opened by OfekGlick about 1 month ago - 1 comment
Labels: question

#362 - [Question] Support for Dict spaces for oberservation space and action space?

Issue - State: open - Opened by OfekGlick about 1 month ago - 1 comment
Labels: question

#359 - [Question] ValueError: the actions value are set to NaN after 10 steps

Issue - State: open - Opened by DavidLudl 2 months ago - 2 comments
Labels: question

#358 - [Question] A question about the cost function of the p3o algorithm

Issue - State: open - Opened by Liqinyan821 3 months ago - 1 comment
Labels: question

#352 - [Question] Passing arguments to environment

Issue - State: open - Opened by zhalehmehrabi 5 months ago - 1 comment
Labels: question

#351 - [Question] How to Manually Control Training Steps in Omnisafe PPO-Lag

Issue - State: closed - Opened by wayne-weiwei 5 months ago - 1 comment
Labels: question

#350 - docs: update appendix

Pull Request - State: closed - Opened by Gaiejj 5 months ago - 1 comment
Labels: documentation

#349 - [Question] How can I record data at each episode during the training ?

Issue - State: open - Opened by Aso2510 6 months ago - 1 comment
Labels: question

#348 - [Question] Some questions about the PPO_lag algorithm

Issue - State: open - Opened by tjruan 6 months ago - 1 comment
Labels: question

#346 - [Question] How to load pretrained model?

Issue - State: open - Opened by qimingRen 7 months ago - 3 comments
Labels: enhancement, question

#345 - [Question]

Issue - State: closed - Opened by Eureke01 7 months ago
Labels: question

#344 - evaluate saved_policy

Issue - State: closed - Opened by Eureka725 7 months ago - 2 comments
Labels: question

#339 - [Question] A question about epoch visualization during the training process

Issue - State: closed - Opened by CrazyTrumpet10 9 months ago - 2 comments
Labels: question

#338 - BrokenProcessPool

Issue - State: closed - Opened by Eureke01 9 months ago - 2 comments
Labels: question

#336 - cuda-based omnisafe environment

Issue - State: closed - Opened by liu-yuntao 9 months ago - 7 comments
Labels: question

#333 - How to use a model that has already been trained through omnisafe?

Issue - State: closed - Opened by Eureke01 9 months ago - 1 comment
Labels: question

#331 - [Question] How to get the result of the example?

Issue - State: closed - Opened by wayne-weiwei 9 months ago - 6 comments
Labels: question

#330 - feat(crabs): refine rendering for saved crabs policies

Pull Request - State: closed - Opened by muchvo 9 months ago - 1 comment

#329 - 输出视频问题

Issue - State: closed - Opened by Eureke01 10 months ago - 8 comments
Labels: question

#328 - feat: support metadrive env

Pull Request - State: closed - Opened by Gaiejj 10 months ago - 1 comment

#327 - feat(cbf): support crabs as a representative control barrier function based algorithm

Pull Request - State: closed - Opened by muchvo 10 months ago - 1 comment

#326 - fix: remove duplicated auto reset

Pull Request - State: closed - Opened by Gaiejj 10 months ago - 1 comment

#325 - feat: support isaac gym interface

Pull Request - State: closed - Opened by Gaiejj 10 months ago - 1 comment

#324 - feat: support safe slac

Pull Request - State: open - Opened by Gaiejj 10 months ago - 1 comment

#323 - feat: support cbf methods

Pull Request - State: open - Opened by Gaiejj 10 months ago - 8 comments

#322 - chore: update changelog

Pull Request - State: closed - Opened by Gaiejj 10 months ago

#321 - 关于sac_lag算法的一些问题

Issue - State: closed - Opened by wtbdky 10 months ago - 20 comments
Labels: question

#320 - about P3O algorithms

Issue - State: closed - Opened by Eureke01 10 months ago - 1 comment
Labels: question

#319 - about pip install

Issue - State: closed - Opened by Eureke01 10 months ago - 2 comments
Labels: question

#318 - [Long-term Support] Officially integrating your algorithm into OmniSafe.

Issue - State: open - Opened by Gaiejj 10 months ago
Labels: enhancement, feature, algorithm

#316 - docs: update README

Pull Request - State: closed - Opened by Gaiejj 10 months ago - 1 comment
Labels: documentation, enhancement

#315 - fix: fix cuda initialization error in experiment grid

Pull Request - State: closed - Opened by Gaiejj 10 months ago - 1 comment
Labels: bug

#314 - [BUG] CUDA ERROR: initialization error in experiment grid

Issue - State: closed - Opened by Gaiejj 10 months ago
Labels: bug

#313 - APPO

Issue - State: open - Opened by Eureke01 10 months ago - 1 comment
Labels: question, algorithm

#312 - Implementation of Decision Diffuser Algorithm

Pull Request - State: closed - Opened by Aidilele 10 months ago - 1 comment

#311 - [Question] Where is CVPO?

Issue - State: closed - Opened by JiwenJ 10 months ago - 2 comments
Labels: question

#310 - feat: support interface of environment customization

Pull Request - State: closed - Opened by Gaiejj 11 months ago - 1 comment

#309 - Dev1.0.1

Pull Request - State: closed - Opened by Aidilele 11 months ago

#308 - [Question] How to use the Dockerfile

Issue - State: closed - Opened by chenyinlin1 11 months ago - 3 comments
Labels: question

#306 - [Question] After train, how to test our own environment?

Issue - State: open - Opened by zhou-ting-hub 12 months ago - 16 comments
Labels: question

#305 - [Question] Customised Environment Carla-gym

Issue - State: closed - Opened by lishizhen1412 12 months ago - 2 comments
Labels: question

#301 - Merge Diffuser Agent

Pull Request - State: closed - Opened by LiuTaowen-Tony about 1 year ago - 6 comments

#300 - Update DecisionDiffuser Algorithm to omnisafe

Pull Request - State: closed - Opened by Aidilele about 1 year ago - 5 comments

#298 - Curriculum Learning with Omnisafe or Safe-Policy-Optimization

Issue - State: closed - Opened by fardinabbasi about 1 year ago - 2 comments
Labels: question

#297 - docs: add missing \lambda

Pull Request - State: closed - Opened by xujinming01 about 1 year ago

#296 - [BUG] NaN error related to model-based RL algos

Issue - State: closed - Opened by familyld about 1 year ago - 2 comments
Labels: bug

#293 - [Question] PPO/TRPO-EarlyTerminated code help

Issue - State: closed - Opened by Obnayuf about 1 year ago - 2 comments
Labels: question

#291 - [Feature Request] Tutorial of customizing environment

Issue - State: closed - Opened by Gaiejj about 1 year ago - 7 comments
Labels: enhancement, feature, environment, algorithm

#289 - docs: fix offline data collection docs

Pull Request - State: closed - Opened by Gaiejj about 1 year ago
Labels: documentation, algorithm

#286 - feat: support discrete environment

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, environment

#285 - How to introduce our environment?

Issue - State: closed - Opened by charleswangyanan over 1 year ago - 59 comments
Labels: question, environment

#283 - [Question]

Issue - State: closed - Opened by QionghuaLiao over 1 year ago - 4 comments
Labels: question

#282 - feat: support A3C parallel in multiple GPUs

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature

#281 - [Question]

Issue - State: closed - Opened by Obnayuf over 1 year ago - 2 comments
Labels: question

#280 - feat(simmer): update config, benchmark results and code style

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, algorithm

#278 - [Question] Customizing my algorithem

Issue - State: closed - Opened by fu-li-ck over 1 year ago - 3 comments
Labels: question

#276 - deps: pin pandas version

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment
Labels: bug, dependency

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#274 - feat: update saute config and benchmarking results

Pull Request - State: open - Opened by Gaiejj over 1 year ago - 1 comment
Labels: enhancement, feature, algorithm

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 9 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#273 - Customizing my environment

Issue - State: closed - Opened by Royalvice over 1 year ago - 2 comments
Labels: question, environment

#272 - docs: pin dependency

Pull Request - State: closed - Opened by Gaiejj over 1 year ago
Labels: bug, documentation, dependency

#271 - [Question] what's the difference between CCE and RCE in model based planning algorithm?

Issue - State: closed - Opened by Jackory over 1 year ago - 2 comments
Labels: question, algorithm

#270 - fix: fix invalid tutorial links

Pull Request - State: closed - Opened by xujinming01 over 1 year ago

#269 - fix(envs): Enable auto reset for MuJoCo envs

Pull Request - State: closed - Opened by dtch1997 over 1 year ago - 1 comment
Labels: bug, environment, algorithm

#268 - [BUG] AutoReset not enabled for MuJoCo envs

Issue - State: closed - Opened by dtch1997 over 1 year ago - 1 comment
Labels: bug

#267 - [Feature Request] Would you be providing an off-policy version of the CRPO method in the later stages?

Issue - State: closed - Opened by guanjiayi over 1 year ago - 2 comments
Labels: enhancement

#266 - feat: support gymnasium style reset API

Pull Request - State: closed - Opened by Gaiejj over 1 year ago
Labels: enhancement, environment

#265 - [Feature Request] update CMDP/Wrapper API to gymnasium API

Issue - State: closed - Opened by luigiberducci over 1 year ago - 2 comments
Labels: enhancement

#263 - feat: support MetaDrive interface

Pull Request - State: closed - Opened by Gaiejj over 1 year ago
Labels: enhancement, feature, environment

#262 - [Feature Request] Will there be any consideration for supporting MetaDriver recently?

Issue - State: closed - Opened by yinglinmonian over 1 year ago - 1 comment
Labels: enhancement

#261 - style: update pre-commit.yaml and fix ruff

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment
Labels: dependency, codestyle

#260 - feat(off-policy): fix final_obsevation setting and support evaluation times configuation

Pull Request - State: closed - Opened by Gaiejj over 1 year ago
Labels: bug, enhancement, algorithm

#259 - [Question] The cost Q-value network is repeatedly add_module

Issue - State: closed - Opened by guanjiayi over 1 year ago - 2 comments
Labels: question

#256 - feat: support new agents tasks and customizing environment guide

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment
Labels: documentation, feature, environment

#254 - feat: rebase CRPO from PPO to TRPO

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment

#253 - chore(off-policy): clear redundant distributed grad average

Pull Request - State: closed - Opened by Gaiejj over 1 year ago - 1 comment

#252 - [Question] Why average actor's gradient in DDPG but not in SAC ?

Issue - State: closed - Opened by Gaiejj over 1 year ago - 2 comments
Labels: question, algorithm, codestyle