Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Chex 1.86 and TF Keras #7

Open
camtice opened this issue Apr 22, 2024 · 1 comment
Open

Chex 1.86 and TF Keras #7

camtice opened this issue Apr 22, 2024 · 1 comment

Comments

@camtice
Copy link

camtice commented Apr 22, 2024

Runs without Error

git clone <this-repo>
cd <repo-home>
conda create -n mpc_main python=3.10
conda activate mpc_main
SYSTEM_VERSION_COMPAT=0 pip install dmlab2d

First Error
pip install -e .

ERROR: Could not find a version that satisfies the requirement tensorflow==2.11.1 (from dm-meltingpot) (from versions: 2.13.0rc0, 2.13.0rc1, 2.13.0rc2, 2.13.0, 2.13.1, 2.14.0rc0, 2.14.0rc1, 2.14.0, 2.14.1, 2.15.0rc0, 2.15.0rc1, 2.15.0, 2.15.1, 2.16.0rc0, 2.16.1)
ERROR: No matching distribution found for tensorflow==2.11.1

First Fix
In setup.py line 121 'tensorflow==2.11.1', to 'tensorflow>=2.13.0',

Second Error
sh ray_patch.sh

ERROR: Attempting to patch Failed to import TF-Keras. Please note that TF-Keras is not installed by default when you install TensorFlow Probability. This is so that JAX-only users do not have to install TensorFlow or TF-Keras. To use TensorFlow Probability with TensorFlow, please install the tf-keras or tf-keras-nightly package. This can be be done through installing the tensorflow-probability[tf] extra. /Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/policy/sample_batch.py

Fix
pip install 'tensorflow-probability[tf]'

Third Error
python baselines/train/run_ray_train.py

Traceback (most recent call last):
File "/Users/camerontice/Desktop/meltingpot/test2/MARL-Melting-pot/baselines/train/run_ray_train.py", line 10, in
from configs import get_experiment_config
File "/Users/camerontice/Desktop/meltingpot/test2/MARL-Melting-pot/baselines/train/configs.py", line 1, in
from meltingpot import substrate
...
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/chex/_src/pytypes.py", line 54, in
PRNGKey = jax.random.KeyArray
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/jax/_src/deprecations.py", line 54, in getattr
raise AttributeError(f"module {module!r} has no attribute {name!r}")
AttributeError: module 'jax.random' has no attribute 'KeyArray'

Fix
setup.py line 109 'chex<0.1.81', to 'chex==0.1.86'

Unresolved Error
python baselines/train/run_ray_train.py --num_workers 4 --num_gpus 0 --local --no-tune --algo ppo --framework torch --exp clean_up --seed 42 --results_dir my_results --logging INFO --wandb False --downsample 8

ValueError: No default encoder config for obs space=Dict('COLLECTIVE_REWARD': Box(-inf, inf, (), float64), 'READY_TO_SHOOT': Box(-inf, inf, (), float64), 'RGB': Box(0, 255, (11, 11, 3), uint8)), lstm=False and attention=False found.

Full Traceback for Final Error
(mpc_main) camerontice@Camerons-Laptop MARL-Melting-pot % python baselines/train/run_ray_train.py --num_workers 4 --num_gpus 0 --local --no-tune --algo ppo --framework torch --exp clean_up --seed 42 --results_dir my_results --logging INFO --wandb False --downsample 8

2024-04-22 11:42:51,127 WARNING deprecation.py:50 -- DeprecationWarning: DirectStepOptimizer has been deprecated. This will raise an error in the future!
2024-04-22 11:42:51,370 - DEBUG - Popen(['git', 'version'], cwd=/Users/camerontice/Desktop/meltingpot/test2/MARL-Melting-pot, stdin=None, shell=False, universal_newlines=False)
2024-04-22 11:42:51,383 - DEBUG - Popen(['git', 'version'], cwd=/Users/camerontice/Desktop/meltingpot/test2/MARL-Melting-pot, stdin=None, shell=False, universal_newlines=False)
2024-04-22 11:42:51,398 - DEBUG - Trying paths: ['/Users/camerontice/.docker/config.json', '/Users/camerontice/.dockercfg']
2024-04-22 11:42:51,398 - DEBUG - Found file at path: /Users/camerontice/.docker/config.json
2024-04-22 11:42:51,398 - DEBUG - Found 'credsStore' section
2024-04-22 11:42:51,432 - DEBUG - [Tracing] Create new propagation context: {'trace_id': '22b069ba99ac4023be6cf6fd3f7f1aaa', 'span_id': '93f5b62e623a58dd', 'parent_span_id': None, 'dynamic_sampling_context': None}
Running trails with the following arguments: Namespace(num_workers=4, num_gpus=0, local=True, no_tune=True, algo='ppo', framework='torch', exp='clean_up', seed=42, results_dir='my_results', logging='INFO', wandb=True, downsample=True, as_test=False)
2024-04-22 11:42:51,484 - DEBUG - Attempting to acquire lock 14508453040 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508453040 acquired on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Attempting to release lock 14508453040 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508453040 released on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Attempting to acquire lock 14508453568 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508453568 acquired on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Attempting to release lock 14508453568 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508453568 released on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Attempting to acquire lock 14508453040 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508453040 acquired on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Attempting to release lock 14508453040 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508453040 released on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Attempting to acquire lock 14508450928 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,485 - DEBUG - Lock 14508450928 acquired on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,486 - DEBUG - Attempting to release lock 14508450928 on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
2024-04-22 11:42:51,486 - DEBUG - Lock 14508450928 released on /tmp/ray/session_2024-04-22_11-42-51_484519_88590/ports_by_node.json.lock
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/subprocess.py:1796: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
self.pid = _posixsubprocess.fork_exec(
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/subprocess.py:1796: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
self.pid = _posixsubprocess.fork_exec(
2024-04-22 11:42:53,056 INFO worker.py:1612 -- Started a local Ray instance. View the dashboard at 127.0.0.1:8265
2024-04-22 11:42:53,398 WARNING algorithm_config.py:2534 -- Setting exploration_config={} because you set _enable_rl_module_api=True. When RLModule API are enabled, exploration_config can not be set. If you want to implement custom exploration behaviour, please modify the forward_exploration method of the RLModule at hand. On configs that have a default exploration config, this must be done with config.exploration_config={}.
The selected option is not tested. You may encounter issues if you use the baseline policy configurations with non-tested algorithms
WARNING! No wandb API key found, running without wandb!
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/air/config.py:803: UserWarning: Setting a RunConfig.local_dir is deprecated and will be removed in the future. If you are not using remote storage,set the RunConfig.storage_path instead. Otherwise, set theRAY_AIR_LOCAL_CACHE_DIR environment variable to control the local cache location.
warnings.warn(
2024-04-22 11:42:53,628 INFO tune.py:666 -- [output] This will use the new output engine with verbosity 0. To disable the new output and use the legacy output engine, set the environment variable RAY_AIR_NEW_OUTPUT=0. For more information, please see ray-project/ray#36949
2024-04-22 11:42:53,637 WARNING deprecation.py:50 -- DeprecationWarning: build_tf_policy has been deprecated. This will raise an error in the future!
2024-04-22 11:42:53,639 WARNING deprecation.py:50 -- DeprecationWarning: build_policy_class has been deprecated. This will raise an error in the future!
2024-04-22 11:42:53,656 WARNING algorithm_config.py:2534 -- Setting exploration_config={} because you set _enable_rl_module_api=True. When RLModule API are enabled, exploration_config can not be set. If you want to implement custom exploration behaviour, please modify the forward_exploration method of the RLModule at hand. On configs that have a default exploration config, this must be done with config.exploration_config={}.
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/gymnasium/spaces/box.py:127: UserWarning: WARN: Box bound precision lowered by casting to float32
logger.warn(f"Box bound precision lowered by casting to {self.dtype}")
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/gymnasium/utils/passive_env_checker.py:141: UserWarning: WARN: The obs returned by the reset() method was expecting numpy array dtype to be float32, actual type: float64
logger.warn(
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/gymnasium/utils/passive_env_checker.py:165: UserWarning: WARN: The obs returned by the reset() method is not within the observation space.
logger.warn(f"{pre} is not within the observation space.")
2024-04-22 11:42:53,680 WARNING algorithm_config.py:2534 -- Setting exploration_config={} because you set _enable_rl_module_api=True. When RLModule API are enabled, exploration_config can not be set. If you want to implement custom exploration behaviour, please modify the forward_exploration method of the RLModule at hand. On configs that have a default exploration config, this must be done with config.exploration_config={}.
╭────────────────────────────────────────────────────────╮
│ Configuration for experiment clean_up │
├────────────────────────────────────────────────────────┤
│ Search algorithm BasicVariantGenerator │
│ Scheduler FIFOScheduler │
│ Number of trials 1 │
╰────────────────────────────────────────────────────────╯

View detailed results here: /Users/camerontice/Desktop/meltingpot/test2/MARL-Melting-pot/my_results/torch/clean_up
To visualize your results with TensorBoard, run: tensorboard --logdir /Users/camerontice/Desktop/meltingpot/test2/MARL-Melting-pot/my_results/torch/clean_up

2024-04-22 11:42:53,799 WARNING algorithm_config.py:2534 -- Setting exploration_config={} because you set _enable_rl_module_api=True. When RLModule API are enabled, exploration_config can not be set. If you want to implement custom exploration behaviour, please modify the forward_exploration method of the RLModule at hand. On configs that have a default exploration config, this must be done with config.exploration_config={}.
:job_id:01000000
:job_id:01000000
2024-04-22 11:42:53,824 WARNING worker.py:854 -- ray.get_gpu_ids() will always return the empty list when called from the driver. This is because Ray does not manage GPU allocations to the driver process.
:task_name:bundle_reservation_check_func
:task_name:bundle_reservation_check_func
:actor_name:PPO
:actor_name:PPO
2024-04-22 11:42:53,841 WARNING algorithm_config.py:2534 -- Setting exploration_config={} because you set _enable_rl_module_api=True. When RLModule API are enabled, exploration_config can not be set. If you want to implement custom exploration behaviour, please modify the forward_exploration method of the RLModule at hand. On configs that have a default exploration config, this must be done with config.exploration_config={}.
2024-04-22 11:42:53,841 WARNING algorithm_config.py:656 -- Cannot create PPOConfig from given config_dict! Property stdout_file not supported.
:actor_name:RolloutWorker
:actor_name:RolloutWorker
/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/gymnasium/spaces/box.py:227: UserWarning: WARN: Casting input x to numpy array.
logger.warn("Casting input x to numpy array.")
2024-04-22 11:42:54,995 WARNING algorithm_config.py:2534 -- Setting exploration_config={} because you set _enable_rl_module_api=True. When RLModule API are enabled, exploration_config can not be set. If you want to implement custom exploration behaviour, please modify the forward_exploration method of the RLModule at hand. On configs that have a default exploration config, this must be done with config.exploration_config={}.
[2024-04-22 11:42:54,999 E 88590 9807680] core_worker.cc:1705: Pushed Error with JobID: 01000000 of type: task with message: ray::RolloutWorker.init() (pid=88590, ip=127.0.0.1, actor_id=cbf960f61968bb00ce1891d601000000, repr=<ray.rllib.evaluation.rollout_worker._modify_class..Class object at 0x3e6436c80>)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/evaluation/rollout_worker.py", line 525, in init
self._update_policy_map(policy_dict=self.policy_dict)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1727, in _update_policy_map
self._build_policy_map(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1838, in _build_policy_map
new_policy = create_policy_for_framework(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/utils/policy.py", line 142, in create_policy_for_framework
return policy_class(observation_space, action_space, merged_config)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/algorithms/ppo/ppo_torch_policy.py", line 49, in init
TorchPolicyV2.init(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/policy/torch_policy_v2.py", line 92, in init
model = self.make_rl_module()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/policy/policy.py", line 424, in make_rl_module
marl_module = marl_spec.build()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/marl_module.py", line 462, in build
module = self.marl_module_class(module_config)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 315, in new_init
previous_init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/marl_module.py", line 58, in init
super().init(config or MultiAgentRLModuleConfig())
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 307, in init
self.setup()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/marl_module.py", line 65, in setup
self._rl_modules[module_id] = module_spec.build()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 104, in build
module = self.module_class(module_config)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 315, in new_init
previous_init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 315, in new_init
previous_init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/torch/torch_rl_module.py", line 82, in init
RLModule.init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 307, in init
self.setup()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/algorithms/ppo/ppo_rl_module.py", line 20, in setup
catalog = self.config.get_catalog()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 189, in get_catalog
return self.catalog_class(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/algorithms/ppo/ppo_catalog.py", line 67, in init
super().init(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 106, in init
self.post_init()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 135, in post_init
self.encoder_config = self.get_encoder_config(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 249, in get_encoder_config
tokenizer_config=cls.get_tokenizer_config(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 333, in get_tokenizer_config
return cls.get_encoder_config(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 307, in get_encoder_config
raise ValueError(
ValueError: No default encoder config for obs space=Dict('COLLECTIVE_REWARD': Box(-inf, inf, (), float64), 'READY_TO_SHOOT': Box(-inf, inf, (), float64), 'RGB': Box(0, 255, (11, 11, 3), uint8)), lstm=False and attention=False found. at time: 1.7138e+09
2024-04-22 11:42:54,999 ERROR actor.py:970 -- Exception raised in creation task: The actor died because of an error raised in its creation task, ray::RolloutWorker.init() (pid=88590, ip=127.0.0.1, actor_id=cbf960f61968bb00ce1891d601000000, repr=<ray.rllib.evaluation.rollout_worker._modify_class..Class object at 0x3e6436c80>)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/evaluation/rollout_worker.py", line 525, in init
self._update_policy_map(policy_dict=self.policy_dict)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1727, in _update_policy_map
self._build_policy_map(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1838, in _build_policy_map
new_policy = create_policy_for_framework(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/utils/policy.py", line 142, in create_policy_for_framework
return policy_class(observation_space, action_space, merged_config)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/algorithms/ppo/ppo_torch_policy.py", line 49, in init
TorchPolicyV2.init(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/policy/torch_policy_v2.py", line 92, in init
model = self.make_rl_module()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/policy/policy.py", line 424, in make_rl_module
marl_module = marl_spec.build()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/marl_module.py", line 462, in build
module = self.marl_module_class(module_config)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 315, in new_init
previous_init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/marl_module.py", line 58, in init
super().init(config or MultiAgentRLModuleConfig())
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 307, in init
self.setup()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/marl_module.py", line 65, in setup
self._rl_modules[module_id] = module_spec.build()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 104, in build
module = self.module_class(module_config)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 315, in new_init
previous_init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 315, in new_init
previous_init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/torch/torch_rl_module.py", line 82, in init
RLModule.init(self, *args, **kwargs)
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 307, in init
self.setup()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/algorithms/ppo/ppo_rl_module.py", line 20, in setup
catalog = self.config.get_catalog()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/rl_module/rl_module.py", line 189, in get_catalog
return self.catalog_class(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/algorithms/ppo/ppo_catalog.py", line 67, in init
super().init(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 106, in init
self.post_init()
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 135, in post_init
self.encoder_config = self.get_encoder_config(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 249, in get_encoder_config
tokenizer_config=cls.get_tokenizer_config(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 333, in get_tokenizer_config
return cls.get_encoder_config(
File "/Users/camerontice/miniconda3/envs/mpc_main/lib/python3.10/site-packages/ray/rllib/core/models/catalog.py", line 307, in get_encoder_config
raise ValueError(
ValueError: No default encoder config for obs space=Dict('COLLECTIVE_REWARD': Box(-inf, inf, (), float64), 'READY_TO_SHOOT': Box(-inf, inf, (), float64), 'RGB': Box(0, 255, (11, 11, 3), uint8)), lstm=False and attention=False found.
@SoyGema
Copy link
Owner

SoyGema commented Apr 22, 2024

Hey @camtice I had the opportunity to check this with @whymath .
We are investigating this issue, but we where able to train locally on mac :

1.Here you have a pip freeze . We checked ray and jax versions

absl-py==2.1.0
aiohttp==3.9.3
aiohttp-cors==0.7.0
aiosignal==1.3.1
annotated-types==0.6.0
anyio==4.3.0
appdirs==1.4.4
astunparse==1.6.3
async-timeout==4.0.3
attrs==23.2.0
cachetools==5.3.3
certifi==2024.2.2
charset-normalizer==3.3.2
chex==0.1.86
click==8.1.7
cloudpickle==3.0.0
colorful==0.5.6
contextlib2==21.6.0
distlib==0.3.8
dm-env==1.6
dm-meltingpot==2.1.1.dev10
dm-tree==0.1.8
dmlab2d==1.0.0
docker-pycreds==0.4.0
e==1.4.5
exceptiongroup==1.2.0
Farama-Notifications==0.0.4
fastapi==0.110.0
filelock==3.13.1
flatbuffers==24.3.7
frozenlist==1.4.1
fsspec==2024.3.1
gast==0.5.4
gitdb==4.0.11
GitPython==3.1.42
google-api-core==2.18.0
google-auth==2.29.0
google-pasta==0.2.0
googleapis-common-protos==1.63.0
grpcio==1.62.1
gymnasium==0.29.1
h11==0.14.0
h5py==3.10.0
httptools==0.6.1
idna==3.6
immutabledict==4.2.0
importlib_metadata==7.1.0
jax==0.4.25
jaxlib==0.4.25
Jinja2==3.1.3
jsonschema==4.21.1
jsonschema-specifications==2023.12.1
keras==3.1.1
libclang==18.1.1
lz4==4.3.3
Markdown==3.6
markdown-it-py==3.0.0
MarkupSafe==2.1.5
mdurl==0.1.2
ml-dtypes==0.3.2
ml_collections==0.1.1
mpmath==1.3.0
msgpack==1.0.8
  1. Please check the README.md file in this section, as we think this might be related to ray
    Identified issues with ray . Let you know that I was able to run this with torch.
    What I did is downloaded the ray project folder Manually and change line 181 as you can see in the README

self.num_outputs = concat_size if not self.post_fc_stack else self.post_fc_stack.num_outputs

I can say that changing this line made it work for me.
LMK how this goes. We might gather on Wednesday afternoon CET time , in case you need a call

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@SoyGema @camtice