Error locating target 'sheeprl.envs.dmc.DMCWrapper'

[LucaZanatta]

Hi all! Nice project!

When I run the following:
python sheeprl exp=dreamer_v3_dmc_walker_walk.yaml

I got the following error:
`
CONFIG
├── algo
│ └── name: dreamer_v3
│ total_steps: 500000
│ per_rank_batch_size: 16
│ run_test: true
│ cnn_keys:
│ encoder:
│ - rgb
│ decoder:
│ - rgb
│ mlp_keys:
│ encoder: []
│ decoder: []
│ world_model:
│ optimizer:
│ target: torch.optim.Adam
│ lr: 0.0001
│ eps: 1.0e-08
│ weight_decay: 0
│ betas:
│ - 0.9
│ - 0.999
│ discrete_size: 32
│ stochastic_size: 32
│ kl_dynamic: 0.5
│ kl_representation: 0.1
│ kl_free_nats: 1.0
│ kl_regularizer: 1.0
│ continue_scale_factor: 1.0
│ clip_gradients: 1000.0
│ decoupled_rssm: false
│ learnable_initial_recurrent_state: true
│ encoder:
│ cnn_channels_multiplier: 32
│ cnn_act: torch.nn.SiLU
│ dense_act: torch.nn.SiLU
│ mlp_layers: 2
│ cnn_layer_norm:
│ cls: sheeprl.models.models.LayerNormChannelLast
│ kw:
│ eps: 0.001
│ mlp_layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ recurrent_model:
│ recurrent_state_size: 512
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ transition_model:
│ hidden_size: 512
│ dense_act: torch.nn.SiLU
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ representation_model:
│ hidden_size: 512
│ dense_act: torch.nn.SiLU
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ observation_model:
│ cnn_channels_multiplier: 32
│ cnn_act: torch.nn.SiLU
│ dense_act: torch.nn.SiLU
│ mlp_layers: 2
│ cnn_layer_norm:
│ cls: sheeprl.models.models.LayerNormChannelLast
│ kw:
│ eps: 0.001
│ mlp_layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ reward_model:
│ dense_act: torch.nn.SiLU
│ mlp_layers: 2
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ bins: 255
│ discount_model:
│ learnable: true
│ dense_act: torch.nn.SiLU
│ mlp_layers: 2
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ actor:
│ optimizer:
│ target: torch.optim.Adam
│ lr: 8.0e-05
│ eps: 1.0e-05
│ weight_decay: 0
│ betas:
│ - 0.9
│ - 0.999
│ cls: sheeprl.algos.dreamer_v3.agent.Actor
│ ent_coef: 0.0003
│ min_std: 0.1
│ max_std: 1.0
│ init_std: 2.0
│ dense_act: torch.nn.SiLU
│ mlp_layers: 2
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ clip_gradients: 100.0
│ unimix: 0.01
│ action_clip: 1.0
│ moments:
│ decay: 0.99
│ max: 1.0
│ percentile:
│ low: 0.05
│ high: 0.95
│ critic:
│ optimizer:
│ target: torch.optim.Adam
│ lr: 8.0e-05
│ eps: 1.0e-05
│ weight_decay: 0
│ betas:
│ - 0.9
│ - 0.999
│ dense_act: torch.nn.SiLU
│ mlp_layers: 2
│ layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ per_rank_target_network_update_freq: 1
│ tau: 0.02
│ bins: 255
│ clip_gradients: 100.0
│ gamma: 0.996996996996997
│ lmbda: 0.95
│ horizon: 15
│ replay_ratio: 0.5
│ learning_starts: 1300
│ per_rank_pretrain_steps: 0
│ per_rank_sequence_length: 64
│ cnn_layer_norm:
│ cls: sheeprl.models.models.LayerNormChannelLast
│ kw:
│ eps: 0.001
│ mlp_layer_norm:
│ cls: sheeprl.models.models.LayerNorm
│ kw:
│ eps: 0.001
│ dense_units: 512
│ mlp_layers: 2
│ dense_act: torch.nn.SiLU
│ cnn_act: torch.nn.SiLU
│ unimix: 0.01
│ hafner_initialization: true
│ player:
│ discrete_size: 32
│
├── buffer
│ └── size: 500000
│ memmap: true
│ validate_args: false
│ from_numpy: false
│ checkpoint: true
│
├── checkpoint
│ └── every: 10000
│ resume_from: null
│ save_last: true
│ keep_last: 5
│
├── env
│ └── id: walker_walk
│ num_envs: 4
│ frame_stack: 1
│ sync_env: true
│ screen_size: 64
│ action_repeat: 2
│ grayscale: false
│ clip_rewards: false
│ capture_video: true
│ frame_stack_dilation: 1
│ actions_as_observation:
│ num_stack: -1
│ noop: You MUST define the NOOP
│ dilation: 1
│ max_episode_steps: -1
│ reward_as_observation: false
│ wrapper:
│ target: sheeprl.envs.dmc.DMCWrapper
│ domain_name: walker
│ task_name: walk
│ width: 64
│ height: 64
│ seed: null
│ from_pixels: true
│ from_vectors: false
│
├── fabric
│ └── target: lightning.fabric.Fabric
│ devices: 1
│ num_nodes: 1
│ strategy: auto
│ accelerator: cuda
│ precision: bf16-mixed
│ callbacks:
│ - target: sheeprl.utils.callback.CheckpointCallback
│ keep_last: 5
│
└── metric
└── log_every: 5000
disable_timer: false
log_level: 1
sync_on_compute: false
aggregator:
target: sheeprl.utils.metric.MetricAggregator
raise_on_missing: false
metrics:
Rewards/rew_avg:
target: torchmetrics.MeanMetric
sync_on_compute: false
Game/ep_len_avg:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/world_model_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/value_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/policy_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/observation_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/reward_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/state_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
Loss/continue_loss:
target: torchmetrics.MeanMetric
sync_on_compute: false
State/kl:
target: torchmetrics.MeanMetric
sync_on_compute: false
State/post_entropy:
target: torchmetrics.MeanMetric
sync_on_compute: false
State/prior_entropy:
target: torchmetrics.MeanMetric
sync_on_compute: false
Grads/world_model:
target: torchmetrics.MeanMetric
sync_on_compute: false
Grads/actor:
target: torchmetrics.MeanMetric
sync_on_compute: false
Grads/critic:
target: torchmetrics.MeanMetric
sync_on_compute: false
logger:
target: lightning.fabric.loggers.TensorBoardLogger
name: 2025-02-27_13-59-20_dreamer_v3_walker_walk_5
root_dir: logs/runs/dreamer_v3/walker_walk
version: null
default_hp_metric: true
prefix: ''
sub_dir: null

Using bfloat16 Automatic Mixed Precision (AMP)
Seed set to 5
Log dir: logs/runs/dreamer_v3/walker_walk/2025-02-27_13-59-20_dreamer_v3_walker_walk_5/version_0
Error executing job with overrides: ['exp=dreamer_v3_dmc_walker_walk.yaml', 'env.sync_env=True']
Error locating target 'sheeprl.envs.dmc.DMCWrapper', set env var HYDRA_FULL_ERROR=1 to see chained exception.`

Am I missing something?

[michele-milesi]

Hi @LucaZanatta, did you follow the instructions for installing dmc environments? https://github.com/Eclectic-Sheep/sheeprl/blob/main/howto/learn_in_dmc.md

[d3tk]

Hi @michele-milesi , I have a slightly related question in reference to the note:
By default the env.sync_env parameter is set to True. We recommend not changing this value for the MuJoCo environments to work properly.

Why is this the case? Does that mean if num_envs > 1 the environments aren't parallel? Or are they parallel just not asynchronous?

Thank you!

[michele-milesi]

Hi, we encountered some issues when using env.sync_env=False with the MuJoCo environments, probably because of multiprocessing (we use AsyncVectorEnv), but we have not explored the issue in depth yet.
When env.sync_env=False, we use the SyncVectorEnv: you instantiate multiple environments, but their execution is not in parallel.

[d3tk]

Thank you for the clarification!
I am noticing that my Plan2Explore Dreamerv3 training is quite slow (9 hours for 55k global steps) on 1 GPU, 64 CPUs, 64 envs.
Do you have any logs of any p2e_dv3 runs on a dm control task for a reference as to how long it should take?

(I can open a new issue if you'd like more information on my hardware/environment etc)

[michele-milesi]

Unfortunately, I do not have any log of a p2e_dv3 run on a dm control task.
If you could open a new issue and include some additional information (including the configuration you are using), I would be grateful.
Thanks