Issues
- 2
- 8
[BUG] Considerable decrease in policy performance after PyTorch 2.5.0 update
#228 opened by alopezrivera - 5
[BUG] Tensordict v0.6.0 is not compatible with rl4co
#229 opened by ShuN6211 - 3
Can't train with the quickstart notebook
#208 opened by Farouc - 3
[Feature Request] Does Floyd-Warshall algorithm perform better on tmat_class ATSP instance generation?
#225 opened by abcdhhhh - 1
- 5
- 4
Code for running GLOP
#222 opened by ujjwaldasari10 - 3
[BUG] CVRPlib inference bug.
#224 opened by Elon-Lau - 1
[BUG] Caculation of `stochastic_prize` in SPCTSPEnv
#219 opened by abcdhhhh - 1
- 2
Error while running EAS
#218 opened by ujjwaldasari10 - 4
[BUG] Failing to call CVRPEnv.local_search
#212 opened by ShuN6211 - 1
Is it possible to generate and load trainning data to the model at every epoch?
#216 opened by ujjwaldasari10 - 2
[Feature Request]Epoch 0/99 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0/2500 0:00:00 • -:--:-- 0.00it/s v_num: o801 val/reward: -17.800
#213 opened by Ynantao - 6
Error while trying to train multiple models for TSP of size 20 and 50.
#205 opened by ujjwaldasari10 - 5
Add support for AGV in the scheduling environment.
#202 opened by lshengjian - 4
[BUG] Cannot click on "Open in Colab" badges
#196 opened by leonlan - 2
[BUG] cant run the quickstart
#206 opened by sunweice - 1
[BUG] Find a mistake in docs
#198 opened by Rubbin1926 - 6
[BUG] Minimalistic Example
#197 opened by leolyg - 3
[Can you provide the environment for python=3.9.18?]
#178 opened by lihaoya5 - 7
[How to change the CVRTW environment so that it can be trained and tested on the Solomon dataset]
#148 opened by lihaoya5 - 4
Convert TSP to ATSP
#108 opened by Mu-Yanchen - 5
Add flexible shop scheduling environment
#168 opened by lshengjian - 1
[BUG] Feature name in StateAugmentation
#139 opened by aziabatz - 2
- 10
Error when I test in vrplib
#137 opened by linCC111 - 0
Change hydra rundir default
#132 opened by LTluttmann - 1
[Please add the am-critic, POMO, and POMO models under the op question to the experiment/archive/ folder]
#136 opened by lihaoya5 - 1
[BUG]When I use the am model to run a PCTSP experiment, an error is reported:TypeError("_DeviceDtypeModuleMixin.__init__() got an unexpected keyword argument 'use_native_sdpa'")
#135 opened by lihaoya5 - 9
RL4CO\rl4co-main\notebooks\tutorials\3-change-encoder.ipynb ,The file is not functioning properly
#121 opened by lihaoya5 - 2
[BUG]When I use the PTRNET model to run a TSP experiment, an error is reported:AttributeError("'PointerNetwork' object has no attribute 'env'")
#134 opened by lihaoya5 - 0
[BUG] Wrong behavior in warmup baseline
#133 opened by LTluttmann - 13
Use my own test set (TSP / CVRP Lib)
#84 opened by WYF99111 - 2
About the training time.
#107 opened by yuanxuanS - 1
[BUG] 'RuntimeError' related to `deepcopy`
#123 opened by Goh-IE - 1
- 1
[Issue] capacity bug
#101 opened by fedebotu - 3
Does rl4co's POMO support SDVRP, OP?
#102 opened by hanseul-jeong - 4
[BUG]'key "demand" not found in TensorDict with keys [\'action_mask\', \'current_node\', \'done\', \'first_node\', \'i\', \'locs\', \'reward\', \'terminated\']'
#104 opened by 1hhix - 4
- 6
Documentation for traveling salesman (https://rl4co.readthedocs.io/en/latest/_collections/tutorials/2-creating-new-env-model.html)
#103 opened by paapu88 - 2
[BUG] torchrl error
#97 opened by aiguoli - 1
[Notice] Updating to new TorchRL and TensorDict
#95 opened by fedebotu - 1
Interface with Flash Attention 2.0
#85 opened by fedebotu - 3
- 2
[Help] The results about the sdvrp environment
#83 opened by kuoiii - 1
[BUG] Can't install rl4co in CPython3.11
#90 opened by hyeok9855 - 3
[BUG] RuntimeError in minimalistic example
#87 opened by yuxiaooye