Skip to content
AllenAct
grouped_action_imitation
Initializing search
allenai/allenact
AllenAct
allenai/allenact
Overview
Installation
Installation
Install AllenAct
Install environments
Download datasets
Getting started
Getting started
Run your first experiment
Primary abstractions
Structure of the codebase
Tutorials
Tutorials
AllenAct Tutorials
Navigation in Minigrid
PointNav in RoboTHOR
Swapping environments
Using a pre-trained model
Off-policy training
OpenAI gym for continuous control
Multi-node ObjectNav training
OpenAI gym for MuJoCo tasks
HowTos
HowTos
Define an experiment
Change rewards and losses
Define a new model
Define a new task
Define a new training pipeline
Projects
Projects
BabyAI baselines
PointNav baselines
ObjectNav baselines
FAQ
Contributing
Licence
API
API
allenact
allenact
_constants
embodiedai
embodiedai
mapping
mapping
mapping_utils
mapping_utils
map_builders
point_cloud_utils
mapping_losses
mapping_models
mapping_models
active_neural_slam
preprocessors
preprocessors
resnet
sensors
sensors
vision_sensors
models
models
aux_models
basic_models
resnet
fusion_models
visual_nav_models
aux_losses
aux_losses
losses
base_abstractions
base_abstractions
experiment_config
misc
task
sensor
preprocessor
distributions
algorithms
algorithms
onpolicy_sync
onpolicy_sync
losses
losses
grouped_action_imitation
imitation
abstract_loss
ppo
kfac
a2cacktr
runner
policy
engine
vector_sampled_tasks
storage
offpolicy_sync
offpolicy_sync
losses
losses
abstract_offpolicy_loss
utils
utils
model_utils
experiment_utils
spaces_utils
system
cacheless_frcnn
misc_utils
multi_agent_viz_utils
viz_utils
tensor_utils
cache_utils
allenact_plugins
allenact_plugins
habitat_plugin
habitat_plugin
habitat_constants
habitat_tasks
habitat_sensors
habitat_environment
habitat_preprocessors
habitat_task_samplers
scripts
scripts
agent_demo
make_map
habitat_utils
lighthouse_plugin
lighthouse_plugin
lighthouse_models
lighthouse_environment
lighthouse_tasks
lighthouse_sensors
lighthouse_util
babyai_plugin
babyai_plugin
babyai_constants
babyai_models
scripts
scripts
truncate_expert_demos
get_instr_length_percentiles
download_babyai_expert_demos
babyai_tasks
ithor_plugin
ithor_plugin
ithor_tasks
ithor_environment
ithor_constants
ithor_util
ithor_sensors
scripts
scripts
make_objectnav_debug_dataset
make_pointnav_debug_dataset
ithor_viz
ithor_task_samplers
robothor_plugin
robothor_plugin
robothor_preprocessors
robothor_task_samplers
robothor_environment
robothor_constants
robothor_distributions
robothor_models
robothor_tasks
scripts
scripts
make_objectnav_debug_dataset
make_pointnav_debug_dataset
robothor_sensors
robothor_viz
minigrid_plugin
minigrid_plugin
minigrid_tasks
minigrid_environments
minigrid_offpolicy
minigrid_sensors
configs
configs
minigrid_nomemory
minigrid_models
manipulathor_plugin
manipulathor_plugin
manipulathor_viz
manipulathor_tasks
manipulathor_task_samplers
manipulathor_constants
armpointnav_constants
manipulathor_sensors
arm_calculation_utils
manipulathor_utils
manipulathor_environment
gym_plugin
gym_plugin
gym_environment
gym_sensors
gym_distributions
gym_models
gym_tasks
constants
projects
projects
gym_baselines
gym_baselines
experiments
experiments
gym_base
gym_humanoid_base
gym_mujoco_base
gym_humanoid_ddppo
mujoco
mujoco
gym_mujoco_swimmer_ddppo
gym_mujoco_reacher_ddppo
gym_mujoco_walker2d_ddppo
gym_mujoco_halfcheetah_ddppo
gym_mujoco_humanoid_ddppo
gym_mujoco_inverteddoublependulum_ddppo
gym_mujoco_ant_ddppo
gym_mujoco_hopper_ddppo
gym_mujoco_invertedpendulum_ddppo
gym_mujoco_ddppo
models
models
gym_models
objectnav_baselines
objectnav_baselines
experiments
experiments
robothor
robothor
objectnav_robothor_base
objectnav_robothor_rgb_resnetgru_ddppo
objectnav_robothor_rgb_resnetgru_dagger
objectnav_robothor_rgbd_resnetgru_ddppo
objectnav_robothor_rgb_resnetgru_ddppo_and_gbc
objectnav_robothor_rgb_unfrozenresnet_gru_ddppo
objectnav_robothor_depth_resnetgru_ddppo
objectnav_mixin_unfrozenresnet_gru
ithor
ithor
objectnav_ithor_rgbd_resnetgru_ddppo
objectnav_ithor_depth_resnetgru_ddppo
objectnav_ithor_rgb_resnetgru_ddppo
objectnav_ithor_base
objectnav_thor_mixin_ddppo_and_gbc
objectnav_thor_base
objectnav_mixin_resnetgru
objectnav_base
objectnav_mixin_ddppo
objectnav_mixin_dagger
models
models
object_nav_models
babyai_baselines
babyai_baselines
experiments
experiments
go_to_local
go_to_local
bc
distributed_bc_offpolicy
dagger
bc_teacher_forcing
distributed_bc_teacher_forcing
ppo
a2c
base
go_to_obj
go_to_obj
bc
dagger
bc_teacher_forcing
ppo
a2c
base
base
pointnav_baselines
pointnav_baselines
experiments
experiments
robothor
robothor
pointnav_robothor_rgbd_simpleconvgru_ddppo
pointnav_robothor_depth_simpleconvgru_ddppo
pointnav_robothor_rgb_simpleconvgru_ddppo
pointnav_robothor_rgb_simpleconvgru_ddppo_and_gbc
pointnav_robothor_base
habitat
habitat
pointnav_habitat_rgb_simpleconvgru_ddppo
pointnav_habitat_rgbd_simpleconvgru_ddppo
pointnav_habitat_base
debug_pointnav_habitat_rgbd_simpleconvgru_ddppo
debug_pointnav_habitat_rgb_simpleconvgru_ddppo
debug_pointnav_habitat_rgb_simpleconvgru_bc
pointnav_habitat_depth_simpleconvgru_ddppo
debug_pointnav_habitat_base
pointnav_base
pointnav_habitat_mixin_ddppo
ithor
ithor
pointnav_ithor_rgbd_simpleconvgru_ddppo
pointnav_ithor_depth_simpleconvgru_ddppo_and_gbc
pointnav_ithor_rgb_simpleconvgru_ddppo
pointnav_ithor_base
pointnav_ithor_depth_simpleconvgru_ddppo
pointnav_mixin_simpleconvgru
pointnav_thor_mixin_ddppo
pointnav_thor_mixin_ddppo_and_gbc
pointnav_thor_base
models
models
point_nav_models
tutorials
tutorials
pointnav_habitat_rgb_ddppo
object_nav_ithor_dagger_then_ppo_one_object
minigrid_offpolicy_tutorial
navtopartner_robothor_rgb_ppo
pointnav_ithor_rgb_ddppo
object_nav_ithor_dagger_then_ppo_one_object_viz
object_nav_ithor_ppo_one_object
minigrid_tutorial_conds
manipulathor_baselines
manipulathor_baselines
armpointnav_baselines
armpointnav_baselines
experiments
experiments
armpointnav_thor_base
armpointnav_base
armpointnav_mixin_ddppo
ithor
ithor
armpointnav_no_vision
armpointnav_ithor_base
armpointnav_depth
armpointnav_rgb
armpointnav_rgbdepth
armpointnav_disjoint_depth
armpointnav_mixin_simplegru
models
models
arm_pointnav_models
base_models
disjoint_arm_pointnav_models
manipulathor_net_utils
tests
tests
mapping
mapping
test_ai2thor_mapping
multiprocessing
multiprocessing
test_frozen_attribs
utils
utils
test_spaces
vision
vision
test_pillow_rescaling
sync_algs_cpu
sync_algs_cpu
test_to_to_obj_trains
manipulathor_plugin
manipulathor_plugin
test_utils
hierarchical_policies
hierarchical_policies
test_minigrid_conditional
allenact.algorithms.onpolicy_sync.losses.grouped_action_imitation
#
[view_source]