Hi, I am using ray to train a multi-agent environment, which contains tuple observation including map (2D image) and poistion (1D) adopting ComplexInputNet.py, with centralized critic approach. I have set my config as follow train_batch_size: 3000 rollout_fragment_length: 100 batch_mode: truncate_…

ValueError: cannot reshape array of size while aligning memory

kyle-playground August 16, 2021, 1:07pm 5

sorry, that’s not the solution, I found out it’s just my personal mistake forgot to return tensor…

Topic		Replies	Views
My observation space cause: ValueError: maximum supported dimension for an ndarray is 32 Configure Algorithm, Training, Evaluation, Scaling	1	695	November 14, 2023
Custom RLModule with LSTM fails to concat episodes of varying lengths together (internal ray error) RLlib	3	55	March 11, 2025
RLlib integration with MLagent RLlib	1	301	April 13, 2023
Error: nan Tensors in PyTorch with Ray RLlib for MARL RLlib	12	1144	August 10, 2024
Running the ray training example got error Configure Algorithm, Training, Evaluation, Scaling	1	412	November 2, 2023