forked from tangger/lerobot
70e3b9248c
- Updated standard deviation parameterization in SACConfig to 'softplus' with defined min and max values for improved stability. - Modified action sampling in SACPolicy to use reparameterized sampling, ensuring better gradient flow and log probability calculations. - Cleaned up log probability calculations in TanhMultivariateNormalDiag for clarity and efficiency. - Increased evaluation frequency in YAML configuration to 50000 for more efficient training cycles. These changes aim to enhance the robustness and performance of the SAC implementation during training and inference.
83 lines
2.3 KiB
Python
83 lines
2.3 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Copyright 2024 The HuggingFace Inc. team.
|
|
# All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from dataclasses import dataclass, field
|
|
|
|
|
|
@dataclass
|
|
class SACConfig:
|
|
input_shapes: dict[str, list[int]] = field(
|
|
default_factory=lambda: {
|
|
"observation.image": [3, 84, 84],
|
|
"observation.state": [4],
|
|
}
|
|
)
|
|
output_shapes: dict[str, list[int]] = field(
|
|
default_factory=lambda: {
|
|
"action": [4],
|
|
}
|
|
)
|
|
|
|
# Normalization / Unnormalization
|
|
input_normalization_modes: dict[str, str] | None = None
|
|
output_normalization_modes: dict[str, str] = field(
|
|
default_factory=lambda: {"action": "min_max"},
|
|
)
|
|
|
|
discount = 0.99
|
|
temperature_init = 1.0
|
|
num_critics = 2
|
|
num_subsample_critics = None
|
|
critic_lr = 3e-4
|
|
actor_lr = 3e-4
|
|
temperature_lr = 3e-4
|
|
critic_target_update_weight = 0.005
|
|
utd_ratio = 2
|
|
state_encoder_hidden_dim = 256
|
|
latent_dim = 50
|
|
target_entropy = None
|
|
critic_network_kwargs = {
|
|
"hidden_dims": [256, 256],
|
|
"activate_final": True,
|
|
}
|
|
actor_network_kwargs = {
|
|
"hidden_dims": [256, 256],
|
|
"activate_final": True,
|
|
}
|
|
policy_kwargs = {
|
|
"tanh_squash_distribution": True,
|
|
"std_parameterization": "softplus",
|
|
"std_min": 0.005,
|
|
"std_max": 5.0,
|
|
}
|
|
)
|
|
output_shapes: dict[str, list[int]] = field(
|
|
default_factory=lambda: {
|
|
"action": [4],
|
|
}
|
|
)
|
|
|
|
state_encoder_hidden_dim: int = 256
|
|
latent_dim: int = 256
|
|
network_hidden_dims: int = 256
|
|
|
|
# Normalization / Unnormalization
|
|
input_normalization_modes: dict[str, str] | None = None
|
|
output_normalization_modes: dict[str, str] = field(
|
|
default_factory=lambda: {"action": "min_max"},
|
|
)
|