Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/abalakrishna123/recovery-rl
/ functions
Functions
314 in github.com/abalakrishna123/recovery-rl
⨍
Functions
314
◇
Types & classes
47
Method
forward
(self, state, action)
recovery_rl/model.py:139
Method
forward
(self, state, action)
recovery_rl/model.py:188
Method
forward
(self, state, action)
recovery_rl/model.py:262
Method
forward
(self, prev_hidden, action)
recovery_rl/model.py:727
Method
forward
(self, observation)
recovery_rl/model.py:769
Method
forward
(self, hidden)
recovery_rl/model.py:821
Method
forward
(self, inputs, ret_logvar=False)
config/image_maze.py:71
Method
forward
(self, inputs, ret_logvar=False)
config/obj_dynamic_extraction.py:71
Method
forward
(self, inputs, ret_logvar=False)
config/obj_extraction.py:71
Method
forward
(self, inputs, ret_logvar=False)
config/navigation1.py:71
Method
forward
(self, inputs, ret_logvar=False)
config/navigation2.py:71
Method
get_desig_pix
(self, target_width, round=True, obj_poses=None)
env/base_mujoco_env.py:99
Method
get_encoding
Get encoded version of image
recovery_rl/VisualMPC.py:257
Method
get_goal_pix
(self, target_width, round=True)
env/base_mujoco_env.py:120
Function
get_offline_data
(num_transitions, images=False, save_rollouts=False,
env/image_maze.py:34
Function
get_offline_data
(num_transitions, task_demos=False, save_rollouts=False)
env/navigation1.py:133
Function
get_offline_data
(num_transitions, images=False, save_rollouts=False)
env/maze.py:34
Function
get_offline_data
(num_transitions, task_demos=False, save_rollouts=False)
env/navigation2.py:133
Method
goal_reached
Checks if the environment hit a goal (if environment has goals) - e.x. if goal is to lift object should return true if object lif
env/base_env.py:50
Function
hard_update
(target, source)
recovery_rl/model.py:37
Method
has_goal
:return: Whether or not environment has a goal
env/base_env.py:58
Method
is_stable
(self, s)
env/navigation1.py:129
Method
is_stable
(self, s)
env/navigation2.py:129
Method
jaw_width
(self)
env/obj_dynamic_extraction.py:185
Method
jaw_width
(self)
env/obj_extraction.py:146
Function
logsumexp
(inputs, dim=None, keepdim=False)
recovery_rl/utils.py:30
Function
make_bool
(arg)
config/default.py:122
Method
ncam
(self)
env/base_mujoco_env.py:165
Method
nn_constructor
(self, model_init_cfg)
config/image_maze.py:151
Method
nn_constructor
(self, model_init_cfg)
config/obj_dynamic_extraction.py:151
Method
nn_constructor
(self, model_init_cfg)
config/obj_extraction.py:151
Method
nn_constructor
(self, model_init_cfg)
config/navigation1.py:155
Method
nn_constructor
(self, model_init_cfg)
config/maze.py:151
Method
nn_constructor
(self, model_init_cfg)
config/navigation2.py:155
Method
object_poses
(self)
env/obj_dynamic_extraction.py:260
Method
object_poses
(self)
env/obj_extraction.py:215
Method
obs_cost_fn
(self, obs)
config/image_maze.py:144
Method
obs_cost_fn
(self, obs)
config/obj_dynamic_extraction.py:144
Method
obs_cost_fn
(self, obs)
config/obj_extraction.py:144
Method
obs_cost_fn
(self, obs)
config/navigation1.py:142
Method
obs_cost_fn
(self, obs)
config/maze.py:144
Method
obs_cost_fn
(self, obs)
config/navigation2.py:142
Method
obs_postproc
(obs, pred)
config/image_maze.py:134
Method
obs_postproc
(obs, pred)
config/obj_dynamic_extraction.py:134
Method
obs_postproc
(obs, pred)
config/obj_extraction.py:134
Method
obs_postproc
(obs, pred)
config/navigation1.py:132
Method
obs_postproc
(obs, pred)
config/navigation2.py:132
Method
obtain_solution
Optimizes the cost function using the provided initial candidate distribution Arguments: init_mean (np.ndarray): The mean of the
recovery_rl/optimizers.py:73
Method
plot_trajectory
(self, states=None)
env/navigation1.py:121
Method
plot_trajectory
(self, states=None)
env/navigation2.py:121
Method
position
(self)
env/obj_dynamic_extraction.py:256
Method
position
(self)
env/obj_extraction.py:211
Function
process_obs
(obs)
recovery_rl/VisualMPC.py:65
Method
push
(self, state, action, reward, next_state, done)
recovery_rl/replay_memory.py:47
Function
read_only
(arg)
config/default.py:130
Method
recovery_thresh
(state, action)
recovery_rl/experiment.py:547
Function
render
(loc)
env/navigation1.py:167
Function
render
(loc)
env/navigation2.py:246
Method
render
Renders the enviornment. Implements custom rendering support. If mode is: - dual: renders both left and main cameras - left:
env/base_mujoco_env.py:49
Method
reset
(self)
env/base_mujoco_env.py:46
Method
reset
Resets the environment. Returns initial observation as well as information needed to recreate initialization :return: obs dict (look
env/base_env.py:31
Method
reset
(self)
env/navigation1.py:91
Method
reset
(self)
env/navigation2.py:90
Method
reset
Resets this controller.
recovery_rl/MPC.py:34
Method
reset
(self)
recovery_rl/optimizers.py:21
Method
reset
(self)
recovery_rl/optimizers.py:70
Method
reset
Resets this controller.
recovery_rl/VisualMPC.py:39
Method
sample
samples a random action from the action space.
env/navigation2.py:115
Method
sample
(self, batch_size, pos_fraction=None)
recovery_rl/replay_memory.py:54
Method
sample
(self, state)
recovery_rl/model.py:425
Method
sample
(self, state)
recovery_rl/model.py:474
Method
sample
(self, state)
recovery_rl/model.py:522
Method
sample
(self, state)
recovery_rl/model.py:610
Method
sample
(self, state)
recovery_rl/model.py:699
Method
sdim
(self)
env/base_mujoco_env.py:161
Method
sdim
:return: Environment's state dimension
env/base_env.py:84
Method
select_action
Gets action from model-free recovery policy Arguments: Current state Returns: ac
recovery_rl/qrisk.py:198
Method
set_goal_obj_pose
(self, pose)
env/base_mujoco_env.py:34
Method
set_y_range
(self, bounds)
env/obj_dynamic_extraction.py:189
Method
set_y_range
(self, bounds)
env/obj_extraction.py:150
Method
setup
(self, cost_function)
recovery_rl/optimizers.py:18
Function
shuffle_rows
(arr)
recovery_rl/VisualMPC.py:55
Method
snapshot_noarm
(self)
env/base_mujoco_env.py:153
Function
soft_update
(target, source, tau)
recovery_rl/model.py:30
Method
step
(self, action)
env/obj_extraction.py:91
Method
step
(self, a)
env/navigation1.py:71
Method
step
(self, a)
env/navigation2.py:70
Method
targ_proc
(obs, next_obs)
config/image_maze.py:138
Method
targ_proc
(obs, next_obs)
config/obj_dynamic_extraction.py:138
Method
targ_proc
(obs, next_obs)
config/obj_extraction.py:138
Method
targ_proc
(obs, next_obs)
config/navigation1.py:136
Method
targ_proc
(obs, next_obs)
config/navigation2.py:136
Method
target_object_height
(self)
env/obj_dynamic_extraction.py:269
Method
target_object_height
(self)
env/obj_extraction.py:224
Method
to
(self, device)
recovery_rl/model.py:440
Method
to
(self, device)
recovery_rl/model.py:481
Method
to
(self, device)
recovery_rl/model.py:527
Method
to
(self, device)
recovery_rl/model.py:617
Method
to
(self, device)
recovery_rl/model.py:704
Method
train
Trains this controller using lists of trajectories.
recovery_rl/MPC.py:29
← previous
next →
201–300 of 314, ranked by callers