search

facebookresearch / BenchMARL

A collection of MARL benchmarks based on TorchRL
https://benchmarl.readthedocs.io/
MIT License
288 stars 42 forks source link

Error Vmas Transport #54

Closed prinshul closed 10 months ago

prinshul commented 10 months ago

python fine_tuned/vmas/vmas_run.py algorithm=mappo task=vmas/transport

Error executing job with overrides: ['algorithm=mappo', 'task=vmas/transport'] Traceback (most recent call last): File "/hdd3/marl_new/BenchMARL/fine_tuned/vmas/vmas_run.py", line 31, in hydra_experiment() File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/main.py", line 94, in decorated_main _run_hydra( File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra _run_app( File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/_internal/utils.py", line 457, in _run_app run_and_report( File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/_internal/utils.py", line 223, in run_and_report raise ex File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/_internal/utils.py", line 220, in run_and_report return func() File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/_internal/utils.py", line 458, in lambda: hydra.run( File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/internal/hydra.py", line 132, in run = ret.return_value File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/core/utils.py", line 260, in return_value raise self._return_value File "/home/iitdpc/miniconda3/envs/marl_bench/lib/python3.9/site-packages/hydra/core/utils.py", line 186, in run_job ret.return_value = task_function(task_cfg) File "/hdd3/marl_new/BenchMARL/fine_tuned/vmas/vmas_run.py", line 25, in hydra_experiment experiment: Experiment = load_experiment_from_hydra(cfg, task_name=task_name) File "/hdd3/marl_new/BenchMARL/benchmarl/hydra_config.py", line 37, in load_experiment_from_hydra return Experiment( File "/hdd3/marl_new/BenchMARL/benchmarl/experiment/experiment.py", line 323, in init self._setup() File "/hdd3/marl_new/BenchMARL/benchmarl/experiment/experiment.py", line 344, in _setup self._setup_collector() File "/hdd3/marl_new/BenchMARL/benchmarl/experiment/experiment.py", line 447, in _setup_collector self.collector = SyncDataCollector( File "/hdd3/marl_new/BenchMARL/torchrl_custom/collectors/collectors.py", line 636, in init self._tensordict = env.reset() File "/hdd3/marl_new/BenchMARL/torchrl_custom/envs/common.py", line 1495, in reset return self._reset_proc_data(tensordict, tensordict_reset) File "/hdd3/marl_new/BenchMARL/torchrl_custom/envs/transforms/transforms.py", line 765, in _reset_proc_data self._reset_check_done(tensordict, tensordict_reset) File "/hdd3/marl_new/BenchMARL/torchrl_custom/envs/common.py", line 1547, in _reset_check_done raise RuntimeError( RuntimeError: The done entry 'done' was (partially) True after a call to reset() in env TransformedEnv( env=VmasEnv(num_envs=600, n_agents=4, batch_size=torch.Size([600]), device=cuda:0) (scenario=transport), transform=Compose( RewardSum(keys=[('agents', 'reward')]))).

matteobettini commented 10 months ago

Duplicate of #43

this should be fixed, upgrade your vmas version