Error running code

i keep getting this error, even though i have downgraded to torch 1.3.1

File “/home/dewe/anaconda3/envs/procgen/lib/python3.7/site-packages/ray/rllib/models/model.py”, line 198, in flatten
return torch.flatten(obs, start_dim=1)
TypeError: flatten(): argument ‘input’ (position 1) must be Tensor, not Tensor

View post 0

Ray Error with TF and CUDA

(topic withdrawn by author, will be automatically deleted in 24 hours unless flagged)

View post 0

Insufficient cluster resources to launch trial

(post withdrawn by author, will be automatically deleted in 24 hours unless flagged)

View post 0

Strategy to achieve objective

I am still un certain of the direction of reaching the objective. do we tweak the hyperparams of the algorithms available and tweak model or are we meant to create brand new algorithms for RL. Or do we just create custom models. I will love to try latest CV models as well. but i don’t know if i am allowed to use PyTorch models created from scratch and using custom algorithms.

View post 0

Insufficient cluster resources to launch trial

ray.tune.error.TuneError: Insufficient cluster resources to launch trial: trial requested 7 CPUs, 0.8999999999999999 GPUs but the cluster has only 2 CPUs, 1 GPUs, 1.37 GiB heap, 0.63 GiB objects (1.0 node:192.168.1.242). Pass queue_trials=True in ray.tune.run() or on the command line to queue trials until the cluster scales up or resources become available.

SO I understand what this error means but i don’t know if i need to repair it before i begin working on the project. I also need some advice on how to fix it.

View post 1