Ecosyste.ms: Issues

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

GitHub / lucasalegre/morl-baselines issues and pull requests

#131 - [Bug?] Issues and Suggestions for Using PGMORL in MORL-Baselines

Issue - State: closed - Opened by hamod-kh about 1 month ago - 2 comments

#130 - ModuleNotFoundError: No module named 'mo_gymnasium.wrappers'

Issue - State: closed - Opened by hejincheng-bit about 2 months ago - 3 comments

#129 - Fix retrieval of observation and action spaces when using wrappers

Pull Request - State: closed - Opened by LucasAlegre 2 months ago
Labels: bug

#128 - [Feature Request] Try torch.compile and cudagraphs

Issue - State: open - Opened by LucasAlegre 3 months ago
Labels: enhancement

#127 - Doc/update version

Pull Request - State: closed - Opened by ffelten 4 months ago

#125 - Add python 3.12 support

Pull Request - State: closed - Opened by ffelten 4 months ago

#124 - Remove Sparsity from metrics logging

Pull Request - State: closed - Opened by ffelten 4 months ago

#123 - Why does the PQL not run in Four Room?

Issue - State: closed - Opened by Saood1810 4 months ago - 2 comments

#122 - Add save_freq option to CAPQL train method

Pull Request - State: closed - Opened by LucasAlegre 4 months ago

#121 - Feature Request: PD MORL

Issue - State: closed - Opened by AsadJeewa 5 months ago - 3 comments

#113 - Add save_freq to CAPQL.train()

Issue - State: closed - Opened by AleNimo 6 months ago - 1 comment

#109 - Migration to gymnasium 1.0

Pull Request - State: closed - Opened by ffelten 6 months ago

#106 - Issue with PGMORL logging global_step

Issue - State: closed - Opened by adamcallaghan0 6 months ago - 7 comments

#100 - why do the GPI-LS and GPI-PD run for a very long time?

Issue - State: closed - Opened by yyicc1108 9 months ago - 4 comments

#99 - Dev eupg

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

#98 - Multi Discrete action space

Issue - State: closed - Opened by Afouene 11 months ago - 3 comments

#97 - Missing instructions on how to train CAPQL agent

Issue - State: closed - Opened by anindyasarkarIITH 11 months ago - 1 comment

#96 - Evaluation of the generated Pareto front

Issue - State: closed - Opened by xwen24 11 months ago - 2 comments

#95 - Make number of sampled weights used to compute utility metrics parameterizable

Pull Request - State: closed - Opened by LucasAlegre 12 months ago
Labels: enhancement

#94 - Chore/remove tensorboard stuff make gym logging optional

Pull Request - State: closed - Opened by ffelten 12 months ago - 2 comments

#93 - AttributeError: module 'cdd' has no attribute 'Matrix'

Issue - State: closed - Opened by PatrickYanZ about 1 year ago - 6 comments

#92 - Why is PCN only working for deterministic envs?

Issue - State: closed - Opened by MikhailTerekhov about 1 year ago - 4 comments

#91 - Debug eupg

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

#90 - Remove dropout at evaluation time on GPI-LS

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

#89 - MORL/D

Pull Request - State: closed - Opened by ffelten about 1 year ago
Labels: enhancement

#88 - issue when calculating the `log_probs` in EUPG.

Issue - State: closed - Opened by omidsbhn about 1 year ago - 3 comments
Labels: bug

#87 - Adding cardinality metric

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

#86 - Fix bug where tolist was called on a float

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

#85 - Bug in PCN due to logging

Issue - State: closed - Opened by wilrop about 1 year ago - 1 comment

#84 - Parallel Hyperparameter Search

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

#83 - Log all training parameters given to the algorithm

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

#82 - Add support for continuous action spaces to PCN

Pull Request - State: closed - Opened by vaidas-sl about 1 year ago - 1 comment

#81 - Generalization of the observations for GPI-LS

Pull Request - State: closed - Opened by AdrienBolling about 1 year ago - 4 comments

#80 - Update README.md

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

#79 - how to run the file named gpi_pd_hopper.py in the example folder?

Issue - State: closed - Opened by man469 about 1 year ago - 2 comments

#78 - Does anyone know how to load the trained model?

Issue - State: closed - Opened by man469 about 1 year ago - 3 comments

#77 - Add bibtex for NeurIPS paper

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

#76 - Using mo-highway environment with morl baselines

Issue - State: closed - Opened by osikazuzanna over 1 year ago - 2 comments

#75 - Use deterministic policies when evaluating PCN

Pull Request - State: closed - Opened by vaidas-sl over 1 year ago - 2 comments

#74 - Feature/hpo

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

#73 - Visualizing the generated Pareto front

Issue - State: closed - Opened by xwen24 over 1 year ago - 5 comments

#72 - The Pareto front generated by minecart is not optimal

Issue - State: closed - Opened by wilrop over 1 year ago - 1 comment

#71 - Help Regarding GPILSContinuousAction Model Convergence

Issue - State: closed - Opened by arshad171 over 1 year ago - 10 comments

#70 - Implement a fix to #69

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

#68 - Multi-core Training PGMORL

Issue - State: closed - Opened by arshad171 over 1 year ago

#67 - Help Regarding Interpreting PGMORL Convergence

Issue - State: closed - Opened by arshad171 over 1 year ago - 2 comments

#66 - Error when running CAPQL-based algorithm on Hopper

Issue - State: closed - Opened by sahandrez over 1 year ago - 4 comments

#65 - Add minecart-deterministic-v0 to envs with known pfs

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

#64 - Support Gymnasium 0.29

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

#63 - Support for image-based observations in GPI-LS and Envelope

Pull Request - State: closed - Opened by LucasAlegre over 1 year ago
Labels: enhancement

#62 - Move util functions to make more sense

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

#61 - Bump to mo-gymnasium 1

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

#60 - Implement fast pareto and convex hull pruning

Pull Request - State: closed - Opened by wilrop over 1 year ago - 8 comments
Labels: enhancement

#59 - Add CAPQL algorithm

Pull Request - State: closed - Opened by LucasAlegre over 1 year ago
Labels: new algo

#58 - tensorboard -> wandb logging

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

#57 - Hyperparameter optimization

Pull Request - State: closed - Opened by lowlypalace over 1 year ago - 2 comments

#56 - Autowrap for highway observation

Pull Request - State: closed - Opened by ffelten almost 2 years ago

#55 - Maintenance/bump precommit tools

Pull Request - State: closed - Opened by ffelten almost 2 years ago

#54 - Fix GPI-LS name in Benchmark script

Pull Request - State: closed - Opened by ffelten almost 2 years ago - 1 comment

#53 - Fix PGMORL evaluation

Pull Request - State: closed - Opened by ffelten almost 2 years ago

#52 - Add GPI-PD and add GPI-LS to benchmark

Pull Request - State: closed - Opened by LucasAlegre almost 2 years ago

#51 - Recover from solver error in OLS

Pull Request - State: closed - Opened by ffelten almost 2 years ago

#50 - Custom Enviroment

Issue - State: closed - Opened by avarbella almost 2 years ago - 2 comments

#49 - Refactor random seed

Pull Request - State: closed - Opened by LucasAlegre almost 2 years ago

#48 - Change PQL to linearly decaying exploration

Pull Request - State: closed - Opened by ffelten almost 2 years ago

#47 - Add num_eval_episodes_for_front parameter

Pull Request - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: enhancement

#46 - Unify exploration strategies

Issue - State: closed - Opened by ffelten almost 2 years ago

#45 - Fix bug in track_policy function that would result in an infinite loop

Pull Request - State: closed - Opened by wilrop almost 2 years ago - 1 comment

#44 - Finish GPI-PD tabular version

Issue - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: enhancement, new algo

#43 - Performance report issue tracker

Issue - State: open - Opened by ffelten almost 2 years ago

#42 - Add CAPQL

Issue - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: new algo

#41 - Feature/benchmarking scripts

Pull Request - State: closed - Opened by ffelten almost 2 years ago - 1 comment

#40 - Write general overview of each algorithm in the docs

Issue - State: open - Opened by LucasAlegre almost 2 years ago - 1 comment
Labels: documentation

#39 - Multi policy MOQlearning learning refactor

Pull Request - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: enhancement

#38 - Remove tensorboard writer

Issue - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: enhancement, good first issue

#37 - Refactor Multi-Policy MO-Qlearning

Issue - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: enhancement

#36 - Unify evaluation metrics across all algorithms

Pull Request - State: closed - Opened by ffelten almost 2 years ago
Labels: enhancement

#35 - Add GPI-PD with continuous actions

Pull Request - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: new algo

#34 - Add PCN algorithm

Pull Request - State: closed - Opened by LucasAlegre almost 2 years ago
Labels: new algo

#33 - Fixed overflow issue of the while loop inside `predict_next_evaluation`

Pull Request - State: closed - Opened by ChrisZonghaoLi about 2 years ago - 2 comments

#32 - Add performance assessment description

Pull Request - State: closed - Opened by ffelten about 2 years ago

#31 - add wandb.log feature to record episode log

Pull Request - State: closed - Opened by PatrickYanZ about 2 years ago - 5 comments

#30 - pass PGMORL params to MOPPO

Pull Request - State: closed - Opened by ChrisZonghaoLi about 2 years ago - 1 comment

#29 - Update pgmorl.py

Pull Request - State: closed - Opened by ChrisZonghaoLi about 2 years ago

#28 - Bump mo-gymnasium

Pull Request - State: closed - Opened by ffelten about 2 years ago

#27 - Add GPI-LS + GPI-PD algorithm

Pull Request - State: closed - Opened by LucasAlegre about 2 years ago
Labels: new algo

#26 - Increase pop size in tests

Pull Request - State: closed - Opened by ffelten about 2 years ago

#25 - [PGMORL] remaining iterations bugfix

Pull Request - State: closed - Opened by mathieu-reymond about 2 years ago - 2 comments
Labels: bug

#24 - Migration to (MO-)Gymnasium

Pull Request - State: closed - Opened by ffelten about 2 years ago - 1 comment

#23 - Feature/add eum

Pull Request - State: closed - Opened by ffelten about 2 years ago - 2 comments

#22 - Init test workflow

Pull Request - State: closed - Opened by ffelten about 2 years ago - 2 comments

#21 - Doc/add pydoc

Pull Request - State: closed - Opened by ffelten about 2 years ago

#20 - Migration from gym to gymnasium (also from mo-gym to mo-gymnasium)

Issue - State: closed - Opened by ChrisZonghaoLi about 2 years ago - 2 comments

#19 - Init doc website

Pull Request - State: closed - Opened by ffelten about 2 years ago

#18 - Modif deployment hook

Pull Request - State: closed - Opened by ffelten about 2 years ago

#17 - Add pre-commit config and correct files

Pull Request - State: closed - Opened by ffelten about 2 years ago

#16 - Base testing

Issue - State: closed - Opened by ffelten about 2 years ago
Labels: enhancement