Ecosyste.ms: Issues

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

GitHub / opendilab/DI-engine issues and pull requests

#857 - feature(nyz&dcy): add LLM/VLM RLHF loss (PPO/GRPO/RLOO)

Pull Request - State: open - Opened by PaParaZz1 8 days ago - 1 comment
Labels: enhancement, algo

#856 - feature(wqj): add vllm collector

Pull Request - State: open - Opened by wqj2004 14 days ago

#855 - polish(pu): delete unused enable_fast_timestep argument

Pull Request - State: closed - Opened by puyuan1996 25 days ago
Labels: config

#854 - feature(nyz): add rlhf dataset

Pull Request - State: closed - Opened by PaParaZz1 28 days ago
Labels: enhancement, data

#853 - feature(wqj): add vllm rlhf collector

Pull Request - State: closed - Opened by wqj2004 about 1 month ago
Labels: enhancement

#852 - AttributeError: 'MultiDiscrete' object has no attribute 'low'

Issue - State: closed - Opened by Rocky-CN about 1 month ago - 3 comments
Labels: bug, env

#851 - enable_fast_timestep

Issue - State: closed - Opened by neal2164 about 2 months ago - 2 comments
Labels: algo

#850 - Noisy Net Issue

Issue - State: open - Opened by neal2164 2 months ago - 2 comments
Labels: bug, algo

#849 - LSTM Layer normalization

Issue - State: closed - Opened by neal2164 2 months ago - 2 comments
Labels: algo

#849 - LSTM Layer normalization

Issue - State: closed - Opened by neal2164 2 months ago - 2 comments
Labels: algo

#848 - Mistake

Issue - State: closed - Opened by perfectconan 2 months ago

#848 - Mistake

Issue - State: closed - Opened by perfectconan 2 months ago

#847 - Epsilon-Greedy Exploration in Hybrid DDPG

Issue - State: closed - Opened by MarkHolmstrom 3 months ago - 2 comments
Labels: algo

#846 - Bug in reset method

Issue - State: closed - Opened by neal2164 3 months ago - 1 comment
Labels: bug, algo

#845 - Reset env_info

Issue - State: closed - Opened by neal2164 3 months ago - 1 comment
Labels: bug, env

#844 - Priority Experience Replay Bug

Issue - State: closed - Opened by neal2164 3 months ago - 1 comment
Labels: bug, data

#843 - Issue with R2D2

Issue - State: closed - Opened by neal2164 3 months ago

#842 - feature(pu): add ddp config of dqn and onppo

Pull Request - State: closed - Opened by puyuan1996 3 months ago
Labels: efficiency optimization, config

#841 - feature(xyy):add HPT model to implement PolicyStem+DuelingHead

Pull Request - State: closed - Opened by luodi-7 3 months ago
Labels: algo

#840 - :feature(xyy):add HPT model to implement PolicyStem+DuelingHead

Pull Request - State: closed - Opened by luodi-7 3 months ago

#839 - add hpt model and corresponding examples.

Pull Request - State: closed - Opened by luodi-7 3 months ago

#838 - conda安装di-engine，无法与python 3.9兼容

Issue - State: closed - Opened by Rocky-CN 3 months ago - 3 comments
Labels: bug

#836 - Bugreport: 运行ptz_simple_spread_qmix_config.py会出错

Issue - State: closed - Opened by agdlfksdhasdoi 3 months ago - 3 comments
Labels: env

#834 - gfootball no obs module

Issue - State: closed - Opened by wenyu427 4 months ago - 1 comment
Labels: env

#833 - feature(pu): add pistonball_env, its unittest and qmix config

Pull Request - State: closed - Opened by puyuan1996 4 months ago
Labels: env, config

#831 - polish(TairanMK): update trading env

Pull Request - State: closed - Opened by TairanMK 5 months ago - 1 comment

#829 - polish(mark): add hybrid action space support to ActionNoiseWrapper

Pull Request - State: closed - Opened by MarkHolmstrom 5 months ago
Labels: enhancement

#828 - feature(whl): add AWR algorithm.

Pull Request - State: closed - Opened by kxzxvbk 5 months ago - 1 comment
Labels: algo

#827 - I'm

Issue - State: closed - Opened by Kindo96 5 months ago - 2 comments

#826 - No Hidden Size List for ContinuousQAC?

Issue - State: closed - Opened by MarkHolmstrom 6 months ago - 1 comment
Labels: discussion, algo

#823 - Observation shape in the custom marl environment

Issue - State: closed - Opened by WangJuan6 7 months ago - 5 comments
Labels: discussion, env

#822 - Export multi-agent policies and shared training

Issue - State: closed - Opened by ardian-selmonaj 7 months ago - 1 comment
Labels: discussion, algo

#821 - feature(zjow): add Implicit Q-Learning

Pull Request - State: closed - Opened by zjowowen 7 months ago
Labels: algo

#820 - Unexpected increase in memory overhead and Multi-GPU guidance in custom environments

Issue - State: closed - Opened by WangJuan6 7 months ago - 2 comments
Labels: discussion, parallel-dist

#818 - About Replicating the PPO Performance in the Hopper-V3 Environment

Issue - State: closed - Opened by hyLiu1994 8 months ago - 3 comments
Labels: env, config

#817 - feature(nyz): adapt DingEnvWrapper to gymnasium

Pull Request - State: closed - Opened by PaParaZz1 8 months ago - 2 comments
Labels: enhancement, env

#816 - How to initialize semantic model in subprocess mode

Issue - State: closed - Opened by WangJuan6 8 months ago - 2 comments
Labels: good first issue, env

#815 - How to define close function in custom environment

Issue - State: closed - Opened by WangJuan6 8 months ago - 3 comments
Labels: good first issue, env

#814 - RuntimeError: mat1 and mat2 shapes cannot be multiplied (4x138 and 64x138)

Issue - State: closed - Opened by WangJuan6 8 months ago - 3 comments
Labels: bug

#813 - How to introduce other optimizers into DI-engine?

Issue - State: open - Opened by weidaolee 8 months ago - 2 comments
Labels: good first issue, algo

#812 - KeyError: 'obs_shape'

Issue - State: closed - Opened by WangJuan6 8 months ago - 2 comments
Labels: bug, config

#811 - style(nyz): relax flask requirement

Pull Request - State: closed - Opened by PaParaZz1 8 months ago - 1 comment
Labels: test

#810 - No example for Trading Environments

Issue - State: closed - Opened by eramosr16 8 months ago - 1 comment
Labels: env, config

#809 - feature(zym): update ppo config to support discrete action space

Pull Request - State: closed - Opened by YinminZhang 8 months ago
Labels: config

#808 - feature(wrh): add EDT code

Pull Request - State: open - Opened by ruiheng123 8 months ago
Labels: algo

#807 - feature(wrh): add taxi env latest version and dqn config

Pull Request - State: closed - Opened by ruiheng123 8 months ago
Labels: config

#806 - feature(wrh): add edt algorithm

Pull Request - State: closed - Opened by ruiheng123 8 months ago
Labels: algo

#805 - style(hus): add new badge (hellogithub) in readme

Pull Request - State: closed - Opened by TuTuHuss 8 months ago
Labels: doc

#803 - 马里奥代码咨询

Issue - State: closed - Opened by wenxueliu 8 months ago - 1 comment
Labels: discussion

#802 - feature(wrh): taxi_dqn_config.py update

Pull Request - State: closed - Opened by ruiheng123 9 months ago - 1 comment
Labels: config

#801 - polish(zym): optimize ppo continuous act

Pull Request - State: closed - Opened by YinminZhang 9 months ago
Labels: config

#800 - gym_anytrading : could not broadcast input array from shape (62,) into shape (20,3) Please help!!

Issue - State: closed - Opened by zhipentian 9 months ago - 3 comments
Labels: bug, env

#799 - feature(wrh): add taxi env

Pull Request - State: closed - Opened by ruiheng123 9 months ago
Labels: env

#798 - bug when running MARL algorithm Qmix in pettingzoo

Issue - State: closed - Opened by cymmerida123 9 months ago - 3 comments
Labels: bug

#796 - cannot run GTrXL demo since v0.5.0

Issue - State: closed - Opened by klcheungaj 9 months ago - 1 comment
Labels: bug

#795 - doc(hus): update discord link and badge in readme

Pull Request - State: closed - Opened by TuTuHuss 10 months ago
Labels: doc

#793 - docker内运行lunarlander_dqn_deploy失败

Issue - State: closed - Opened by Eric-Zhao1 10 months ago - 6 comments
Labels: bug, docker

#792 - question for SMAC

Issue - State: closed - Opened by bihanbihan 10 months ago - 3 comments
Labels: env

#790 - how to get the ckpt file?

Issue - State: closed - Opened by SiriusZbz 10 months ago - 2 comments
Labels: bug

#789 - TD3应用混合动作空间报错，AssertionError

Issue - State: closed - Opened by dajianer 11 months ago - 2 comments
Labels: bug

#788 - feature(nyz): add GPU utils

Pull Request - State: closed - Opened by PaParaZz1 11 months ago - 1 comment
Labels: efficiency optimization

#787 - 如何获取每个episode的reward值

Issue - State: closed - Opened by dajianer 11 months ago - 1 comment
Labels: discussion

#786 - fix(zjow): fix complex obs demo for ppo pipeline

Pull Request - State: closed - Opened by zjowowen 11 months ago - 1 comment
Labels: bug

#785 - fix(dajianer): add 'collect_kwargs' to the keep function of OnlineRLContext

Pull Request - State: closed - Opened by dajianer 11 months ago - 1 comment
Labels: bug

#784 - 混合动作空间环境，PPO使用gae_estimator报错

Issue - State: closed - Opened by dajianer 11 months ago - 3 comments
Labels: bug

#783 - feature(xrk): add q-transformer

Pull Request - State: open - Opened by rongkunxue 11 months ago
Labels: algo

#782 - env(rjy): add ising model env

Pull Request - State: closed - Opened by nighood 12 months ago - 1 comment
Labels: env

#781 - feature(xrk): add new env named Flozen Lake and DQN algorithm.

Pull Request - State: closed - Opened by rongkunxue 12 months ago - 1 comment
Labels: env

#780 - feature(xrk): add new env named Flozen Lake and DQN algorithm.

Pull Request - State: closed - Opened by rongkunxue 12 months ago

#779 - feature(xrk): add new env named Flozen Lake and DQN algorithm.

Pull Request - State: closed - Opened by rongkunxue 12 months ago
Labels: env

#778 - feature(ooo): add deprecated function decorator

Pull Request - State: closed - Opened by ooooo-create 12 months ago - 2 comments
Labels: enhancement

#776 - fix(eltociear): typo in config.py

Pull Request - State: closed - Opened by eltociear about 1 year ago - 1 comment
Labels: typo

#775 - FQF logit computation

Issue - State: closed - Opened by dmartinezbaselga about 1 year ago - 3 comments
Labels: discussion, algo

#774 - feature(nyz): add MADDPG pettingzoo example

Pull Request - State: closed - Opened by PaParaZz1 about 1 year ago
Labels: algo, config

#773 - Implementation of Mean-Field MARL algorithm

Issue - State: closed - Opened by openRiemann about 1 year ago - 3 comments
Labels: algo

#771 - feature(zc): add MetaDiffuser and prompt-dt

Pull Request - State: open - Opened by Super1ce about 1 year ago
Labels: algo

#770 - record a video

Issue - State: closed - Opened by zhixiongzh about 1 year ago - 2 comments

#769 - gym soccer是否有文档？ 其参数设置以及action的类型该如何写

Issue - State: closed - Opened by Joylessss about 1 year ago - 3 comments
Labels: env

#768 - polish(pu): polish comments in a2c/bcq/fqf/ibc policy

Pull Request - State: closed - Opened by puyuan1996 about 1 year ago - 1 comment
Labels: config, doc

#767 - polish(pu): polish NGU atari configs

Pull Request - State: closed - Opened by puyuan1996 about 1 year ago - 1 comment
Labels: config

#765 - 尝试使用自定义环境出现问题

Issue - State: closed - Opened by HawkQ about 1 year ago - 2 comments
Labels: env

#764 - polish(rjy): polish pg/iqn/edac policy doc

Pull Request - State: closed - Opened by nighood about 1 year ago
Labels: doc

#763 - doc(zjow): polish the notation of classes and functions in torch_utils and utils

Pull Request - State: closed - Opened by zjowowen about 1 year ago - 1 comment
Labels: doc

#762 - doc(rjy): polish d4pg/ppg/qrdqn policy doc

Pull Request - State: closed - Opened by nighood about 1 year ago - 1 comment
Labels: doc

#761 - fix(pu): fix hppo entropy_weight to avoid nan error in log_prob

Pull Request - State: closed - Opened by puyuan1996 about 1 year ago - 1 comment
Labels: bug

#760 - H-PPO算法运行失败

Issue - State: closed - Opened by Root970103 about 1 year ago - 7 comments
Labels: bug

#759 - fix(zjow): fix bug in cliffwalking env

Pull Request - State: closed - Opened by zjowowen about 1 year ago
Labels: bug

#758 - doc(zjow): add API doc for ding agent

Pull Request - State: closed - Opened by zjowowen about 1 year ago
Labels: doc

#757 - feature(zjow): add qgpo policy for new DI-engine pipeline

Pull Request - State: closed - Opened by zjowowen about 1 year ago - 1 comment
Labels: algo

#755 - polish(rjy): polish the comments of collate_fn/profiler_helper/metric

Pull Request - State: closed - Opened by nighood about 1 year ago
Labels: doc

#754 - feature(luyd): fix dt new pipeline of mujoco

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

#753 - feature(zjow): add envpool new pipeline

Pull Request - State: open - Opened by zjowowen about 1 year ago
Labels: enhancement

#752 - polish(rjy): polish comments in normalizer_helper and lock_helper

Pull Request - State: closed - Opened by nighood over 1 year ago
Labels: doc

#750 - what algorithm do you use to sovle the overcooked problem? MADDPG?

Issue - State: closed - Opened by frandoLin over 1 year ago - 3 comments
Labels: discussion