MCPcopy Create free account

hub / github.com/ReinFlow/ReinFlow / functions

Functions864 in github.com/ReinFlow/ReinFlow

⨍ Functions 864◇ Types & classes 170↳ Endpoints 1
Methodloss_actor
(self, obs)
model/rl/gaussian_ibrl.py:137
Methodloss_actor
(self, obs, alpha)
model/rl/gaussian_rlpd.py:122
Methodloss_actor
(self, obs, alpha)
model/rl/gaussian_calql.py:195
Methodloss_critic
(self, obs, next_obs, actions, rewards, terminated, gamma)
model/diffusion/diffusion_dql.py:65
Methodloss_critic
(self, obs, advantages)
model/diffusion/diffusion_awr.py:50
Methodloss_critic
(self, obs, next_obs, actions, rewards, terminated, gamma)
model/diffusion/diffusion_qsm.py:87
Methodloss_critic
(self, obs, next_obs, actions, rewards, terminated, gamma)
model/diffusion/diffusion_dipo.py:67
Methodloss_critic
Compute the critic loss using mean squared error between predicted and target Q-values, with debug information. Use the one-step actor's actio
model/flow/ft_baselines/fql.py:169
Methodloss_critic
( self, obs, next_obs, actions, rewards, terminated, g
model/gaussian/gaussian_ibrl.py:91
Methodloss_critic
(self, obs, advantages)
model/gaussian/gaussian_awr.py:46
Methodloss_critic
( self, obs, next_obs, actions, rewards, terminated, g
model/gaussian/gaussian_rlpd.py:84
Methodloss_critic
( self, obs, next_obs, actions, random_actions, rewards,
model/gaussian/gaussian_calql.py:78
Methodloss_critic
( self, obs, next_obs, actions, rewards, terminated, g
model/gaussian/gaussian_sac.py:52
Methodloss_critic
( self, obs, next_obs, actions, rewards, terminated, g
model/rl/gaussian_ibrl.py:91
Methodloss_critic
( self, obs, next_obs, actions, rewards, terminated, g
model/rl/gaussian_rlpd.py:84
Methodloss_critic
( self, obs, next_obs, actions, random_actions, rewards,
model/rl/gaussian_calql.py:78
Methodloss_critic
( self, obs, next_obs, actions, rewards, terminated, g
model/rl/gaussian_sac.py:53
Methodloss_temperature
(self, obs, alpha, target_entropy)
model/gaussian/gaussian_rlpd.py:136
Methodloss_temperature
(self, obs, alpha, target_entropy)
model/gaussian/gaussian_calql.py:206
Methodloss_temperature
(self, obs, alpha, target_entropy)
model/gaussian/gaussian_sac.py:93
Methodloss_temperature
(self, obs, alpha, target_entropy)
model/rl/gaussian_rlpd.py:136
Methodloss_temperature
(self, obs, alpha, target_entropy)
model/rl/gaussian_calql.py:206
Methodloss_temperature_log
(self, obs, logalpha, target_entropy)
model/gaussian/gaussian_sac.py:103
Methodmake_dataset
(self)
agent/finetune/reinflow/buffer.py:302
Methodmake_dataset
(self)
agent/finetune/reinflow/buffer.py:366
Methodmake_dataset
bug fix:
agent/finetune/reinflow/buffer.py:621
Methodmake_dataset
bug fix:
agent/finetune/reinflow/buffer.py:695
Methodmake_dataset
(self)
agent/finetune/reinflow/buffer.py:859
Methodmake_dataset
(self)
agent/finetune/reinflow/buffer.py:939
Methodmake_dataset
bug fix:
agent/finetune/reinflow/buffer.py:1194
Methodmake_dataset
bug fix:
agent/finetune/reinflow/buffer.py:1270
Methodmake_indices
skip last step of truncated episodes
agent/dataset/sequence.py:253
Methodmarginal_prob
Parameters to determine the marginal distribution of the SDE, $p_t(x)$.
model/diffusion/sde_lib.py:94
Methodmarginal_prob
(self, x, t)
model/diffusion/sde_lib.py:209
Functionmat2posQuat
Converts a 4x4 rotation matrix to a position and a quaternion
agent/dataset/d3il_dataset/geo_transform.py:336
Functionode_func
(t, x)
model/diffusion/exact_likelihood.py:148
Methodp_losses
reward-weighted
model/diffusion/diffusion_rwr.py:57
Methodp_losses
not reward-weighted, same as diffusion.py
model/diffusion/diffusion_idql.py:119
Methodp_mean_var
( self, x, t, cond, index=None, deterministic=False, )
model/diffusion/diffusion_eval.py:92
Functionplot_3d_eval_statistics_groups
Plot multiple 3D surface plots in a single figure to compare evaluation statistics across different groups, such as finetuned and pretrained
agent/eval/visualize/utils.py:487
Functionpoint_euler2euler
(euler)
agent/dataset/d3il_dataset/geo_transform.py:257
Functionpoint_quat2quat
(quat)
agent/dataset/d3il_dataset/geo_transform.py:281
FunctionposRotMat2TFMat
Converts a position and a 3x3 rotation matrix to a 4x4 transformation matrix
agent/dataset/d3il_dataset/geo_transform.py:328
Functionprint_structure
(name, obj)
data_process/read_hdf5.py:33
Functionprint_type_and_shape
(var_name, var)
util/logging_custom.py:66
Methodprior_logp
(self, z)
model/diffusion/sde_lib.py:221
Methodprior_sampling
Generate one sample from the prior distribution, $p_T(x)$.
model/diffusion/sde_lib.py:99
Methodprior_sampling
(self, shape)
model/diffusion/sde_lib.py:218
Functionquat2axisangle
(quat)
agent/dataset/d3il_dataset/geo_transform.py:234
Functionquat2point_quat
(quat)
agent/dataset/d3il_dataset/geo_transform.py:267
Functionquat_identity
()
agent/dataset/d3il_dataset/geo_transform.py:230
Functionquat_rot_vec
(q, v0)
agent/dataset/d3il_dataset/geo_transform.py:223
Methodrender
(self, *args, **kwargs)
env/gym_utils/async_vector_env.py:732
Methodrender
(self, **kwargs)
env/gym_utils/wrapper/mujoco_locomotion_lowdim.py:95
Methodrender
(self, mode="rgb_array", width:int=256, height:int=256)
env/gym_utils/wrapper/d3il_lowdim.py:110
Methodreset
Ignore passed-in arguments like seed
env/gym_utils/wrapper/robomimic_lowdim.py:119
Methodreset
(self)
agent/finetune/reinflow/buffer.py:281
Methodreset
(self)
agent/finetune/reinflow/buffer.py:352
Methodreset
(self)
agent/finetune/reinflow/buffer.py:504
Methodreset
(self)
agent/finetune/reinflow/buffer.py:680
Methodreset
(self)
agent/finetune/reinflow/buffer.py:837
Methodreset
(self)
agent/finetune/reinflow/buffer.py:913
Methodreset
(self)
agent/finetune/reinflow/buffer.py:1070
Methodreset
(self)
agent/finetune/reinflow/buffer.py:1255
Methodreset_actor_optimizer
Not used anywhere currently
agent/finetune/reinflow/train_ppo_agent.py:236
Methodreset_actor_optimizer
Not used anywhere currently
agent/finetune/dppo/train_ppo_agent.py:113
Methodreset_arg
(self, options_list=None)
env/gym_utils/wrapper/furniture.py:125
Methodreset_async
Send the calls to :obj:`reset` to each sub-environment. Raises ------ ClosedEnvironmentError If the environment w
env/gym_utils/async_vector_env.py:262
Methodreset_async
(self, **kwargs)
env/gym_utils/vector_env.py:269
Methodreset_env
(self, env_ind, verbose=False)
agent/eval/eval_agent_base.py:193
Methodreset_env
(self, env_ind, verbose=False)
agent/finetune/train_agent.py:203
Methodreset_env
(self, buffer_device='cpu')
agent/finetune/reinflow/train_ppo_agent.py:297
Methodreset_env
(self, env_ind, verbose=False)
agent/pretrain/train_agent.py:554
Methodreset_env_all
(self, verbose=False, options_venv=None, **kwargs)
agent/finetune/train_agent.py:184
Methodreset_one_arg
(self, env_ind=None, options=None)
env/gym_utils/wrapper/furniture.py:128
Methodreset_wait
Parameters ---------- timeout : int or float, optional Number of seconds before the call to `reset_wait` times ou
env/gym_utils/async_vector_env.py:307
Methodreset_wait
(self, **kwargs)
env/gym_utils/vector_env.py:272
Methodreset_wait
( self, seed: Optional[Union[int, List[int]]] = None, return_info: bool = False,
env/gym_utils/sync_vector_env.py:113
Functionround_to_straight_angles
Returns closest angle modulo 90 degrees
agent/dataset/d3il_dataset/geo_transform.py:305
Methodrun
(self)
agent/finetune/train_agent.py:159
Methodrun
(self)
agent/finetune/reinflow/train_ppo_diffusion_img_agent.py:238
Methodrun
(self)
agent/finetune/reinflow/train_ppo_flow_agent.py:155
Methodrun
(self)
agent/finetune/reinflow/train_ppo_flow_img_agent.py:157
Methodrun
(self)
agent/finetune/reinflow/train_agent.py:158
Methodrun
(self)
agent/finetune/reinflow/train_ppo_gaussian_agent.py:58
Methodrun
(self)
agent/finetune/reinflow/train_ppo_shortcut_img_agent.py:152
Methodrun
(self)
agent/finetune/reinflow/train_ppo_shortcut_agent.py:151
Methodrun
(self)
agent/finetune/reinflow/train_ppo_diffusion_agent.py:214
Methodrun
(self)
agent/finetune/flow_baselines/train_sac_agent.py:92
Methodrun
(self)
agent/finetune/flow_baselines/train_fql_agent.py:148
Methodrun
(self)
agent/finetune/offlinerl_baselines/train_rlpd_agent.py:112
Methodrun
(self)
agent/finetune/offlinerl_baselines/train_calql_agent.py:124
Methodrun
(self)
agent/finetune/offlinerl_baselines/train_ibrl_agent.py:105
Methodrun
(self)
agent/finetune/dppo/train_ppo_gaussian_img_agent.py:59
Methodrun
(self)
agent/finetune/dppo/train_ppo_diffusion_img_agent.py:61
Methodrun
(self)
agent/finetune/dppo/train_ppo_gaussian_agent.py:47
Methodrun
(self)
agent/finetune/dppo/train_ppo_diffusion_agent.py:69
Methodrun
(self)
agent/finetune/diffusion_baselines/train_idql_diffusion_agent.py:120
Methodrun
(self)
agent/finetune/diffusion_baselines/train_rwr_diffusion_agent.py:75
Methodrun
(self)
agent/finetune/diffusion_baselines/train_awr_diffusion_agent.py:147
← previousnext →701–800 of 864, ranked by callers