Functions — github.com/chenbq/CAVDN

hub / github.com/chenbq/CAVDN / functions

Functions307 in github.com/chenbq/CAVDN

⨍ Functions 307◇ Types & classes 66

↓ 21 callersMethodstep

Returns reward, terminated, info.

env/UAV_env.py:47

↓ 13 callersFunctionsoft_update

Perform DDPG soft update (move target params toward source based on weight factor tau) Inputs: target (torch.nn.Module): Net to c

common/utils.py:5

↓ 9 callersMethodclose

(self)

env/UAV_env.py:102

↓ 7 callersMethodchoose_action

(self, obs, last_action, agent_num, avail_actions, epsilon, maven_z=None, evaluate=False)

agent/agent.py:45

↓ 7 callersMethodsample

(self, batch_size)

common/replay_buffer.py:55

↓ 6 callersMethod__init__

(self)

env/multiagent_com/rendering.py:154

↓ 6 callersMethodget_avail_agent_actions

Returns the available actions for agent_id.

env/UAV_env.py:87

↓ 5 callersMethodadd_attr

(self, attr)

env/multiagent_com/rendering.py:165

↓ 5 callersFunctionget_array

(name, mode='np')

plot_reward_all.py:24

↓ 5 callersMethodrender

(self)

env/multiagent_com/rendering.py:157

↓ 5 callersMethodreset

Returns initial observations and states.

env/UAV_env.py:95

↓ 5 callersMethodseed

(self)

env/UAV_env.py:105

↓ 5 callersMethodset_color

(self, r, g, b, alpha=1)

env/multiagent_com/rendering.py:167

↓ 4 callersMethod__init__

(self, input_shape, args)

network/base_net.py:221

↓ 4 callersFunction_add_attrs

(geom, attrs)

env/multiagent_com/rendering.py:147

↓ 4 callersMethod_get_obs

(self, agent)

env/multiagent_com/environment.py:127

↓ 4 callersMethodadd_onetime

(self, geom)

env/multiagent_com/rendering.py:83

↓ 4 callersMethodget_state

Returns the global state.

env/UAV_env.py:68

↓ 4 callersMethodinit_hidden

(self, episode_num)

policy/FC.py:178

↓ 4 callersMethodlearn

在learn的时候，抽取到的数据是四维的，四个维度分别为 1——第几个episode 2——episode中第几个transition 3——第几个agent的数据 4——具体obs维度。因为在选动作时不仅需要输入当前的inputs，还要给神经网络输入hidden_

policy/FC.py:59

↓ 4 callersMethodsave_model

(self, train_step)

policy/FC.py:183

↓ 3 callersMethodgenerate_episode

(self, episode_num=None, evaluate=False)

common/rollout.py:23

↓ 3 callersMethodget_action_weights

(self, obs, last_action)

agent/agent.py:225

↓ 3 callersMethodget_obs

Returns all agent observations in a list.

env/UAV_env.py:53

↓ 3 callersFunctionmake_circle

(radius=10, res=30, filled=True)

env/multiagent_com/rendering.py:243

↓ 3 callersMethodset_translation

(self, newx, newy)

env/multiagent_com/rendering.py:188

↓ 2 callersMethod__init__

(self, args)

network/qtran_net.py:101

↓ 2 callersMethod__init__

(self, input_shape, args)

network/maven_net.py:21

↓ 2 callersMethod__init__

(self)

env/multiagent_com/core.py:64

↓ 2 callersMethod_reset_render

(self)

env/multiagent_com/environment.py:199

↓ 2 callersMethodadd_geom

(self, geom)

env/multiagent_com/rendering.py:80

↓ 2 callersMethodclose

(self)

env/multiagent_com/rendering.py:66

↓ 2 callersMethoddisable

(self)

env/multiagent_com/rendering.py:173

↓ 2 callersMethodenable

(self)

env/multiagent_com/rendering.py:171

↓ 2 callersMethodevaluate

(self)

runner.py:95

↓ 2 callersFunctionget_centralv_args

(args)

common/arguments.py:132

↓ 2 callersFunctionget_coma_args

(args)

common/arguments.py:39

↓ 2 callersFunctionget_commnet_args

(args)

common/arguments.py:202

↓ 2 callersFunctionget_common_args

()

common/arguments.py:9

↓ 2 callersMethodget_env_info

(self)

env/UAV_env.py:112

↓ 2 callersFunctionget_g2anet_args

(args)

common/arguments.py:210

↓ 2 callersFunctionget_mixer_args

(args)

common/arguments.py:78

↓ 2 callersMethodget_qtran

(self, batch, local_opt_actions, hidden_evals, hidden_targets=None, hat=False)

policy/qtran_alt.py:240

↓ 2 callersMethodget_qtran

(self, batch, hidden_evals, hidden_targets, local_opt_actions, hat=False)

policy/qtran_base.py:218

↓ 2 callersFunctionget_reinforce_args

(args)

common/arguments.py:170

↓ 2 callersMethodintegrate_position_state

(self,agent)

env/multiagent_com/core.py:131

↓ 2 callersFunctionmake_polygon

(v, filled=True)

env/multiagent_com/rendering.py:253

↓ 2 callersMethodmake_world

(self)

env/multiagent_com/scenarios/uav_com.py:26

↓ 2 callersMethodplt

(self, num)

runner.py:109

↓ 2 callersMethodrender

(self)

env/UAV_env.py:99

↓ 2 callersMethodreset

(self)

env/multiagent_com/environment.py:103

↓ 2 callersMethodsave_replay

Save a replay.

env/UAV_env.py:108

↓ 2 callersMethodstep

(self)

env/multiagent_com/core.py:123

↓ 2 callersMethodtrain

(self, batch, train_step, epsilon=None)

agent/agent.py:121

↓ 2 callersMethodupdate_agent_access_state

(self, agent)

env/multiagent_com/core.py:152

↓ 1 callersMethod__init__

(self, args, hidden_shape=32)

network/coord_net.py:36

↓ 1 callersMethod_choose_action_from_softmax

:param inputs: # q_value of all actions

agent/agent.py:86

↓ 1 callersMethod_get_action_prob

(self, batch, max_episode_len, epsilon)

policy/coma.py:232

↓ 1 callersMethod_get_action_prob

(self, batch, max_episode_len, epsilon)

policy/reinforce.py:131

↓ 1 callersMethod_get_action_prob

(self, batch, max_episode_len, epsilon)

policy/central_v.py:147

↓ 1 callersMethod_get_actor_inputs

(self, batch, transition_idx)

policy/coma.py:209

↓ 1 callersMethod_get_actor_inputs

(self, batch, transition_idx)

policy/reinforce.py:108

↓ 1 callersMethod_get_actor_inputs

(self, batch, transition_idx)

policy/central_v.py:124

↓ 1 callersMethod_get_critic_input_shape

(self)

policy/coma.py:76

↓ 1 callersMethod_get_critic_inputs

(self, batch, transition_idx, max_episode_len)

policy/coma.py:127

↓ 1 callersMethod_get_done

(self, agent)

env/multiagent_com/environment.py:134

↓ 1 callersMethod_get_evl_data

(self)

env/multiagent_com/environment.py:121

↓ 1 callersMethod_get_individual_inputs

(self, batch, transition_idx)

policy/qtran_alt.py:213

↓ 1 callersMethod_get_individual_inputs

(self, batch, transition_idx)

policy/qtran_base.py:191

↓ 1 callersMethod_get_individual_q

(self, batch, max_episode_len)

policy/qtran_alt.py:182

↓ 1 callersMethod_get_individual_q

(self, batch, max_episode_len)

policy/qtran_base.py:156

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/FC.py:112

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/iql.py:106

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/vdn.py:123

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/FC_QMIX_add.py:115

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/maven.py:163

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/FC_QMIX.py:136

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/qmix.py:122

↓ 1 callersMethod_get_inputs

(self, batch, transition_idx)

policy/FC_ACML.py:141

↓ 1 callersMethod_get_max_episode_len

(self, batch)

agent/agent.py:108

↓ 1 callersMethod_get_max_episode_len

(self, batch)

agent/agent.py:193

↓ 1 callersMethod_get_max_episode_len

(self, batch)

agent/agent.py:293

↓ 1 callersMethod_get_max_episode_len

(self, batch)

agent/agent.py:395

↓ 1 callersMethod_get_q_values

(self, batch, max_episode_len)

policy/coma.py:186

↓ 1 callersMethod_get_returns

(self, r, mask, terminated, max_episode_len)

policy/reinforce.py:97

↓ 1 callersMethod_get_reward

(self, agent)

env/multiagent_com/environment.py:140

↓ 1 callersMethod_get_storage_idx

(self, inc=None)

common/replay_buffer.py:62

↓ 1 callersMethod_get_v_values

(self, batch, max_episode_len)

policy/central_v.py:107

↓ 1 callersMethod_prepare_attentional_mechanism_input

(self, Wh)

network/base_net.py:160

↓ 1 callersMethod_set_move_action

(self, action, agent, action_space, time=None)

env/multiagent_com/environment.py:157

↓ 1 callersMethod_train_critic

(self, batch, max_episode_len, train_step)

policy/coma.py:267

↓ 1 callersMethod_train_critic

(self, batch, max_episode_len, train_step)

policy/central_v.py:182

↓ 1 callersFunctionaction_from_pos

(pos_l, pos_a)

main_eval.py:109

↓ 1 callersFunctionalg_eval

(runner, env)

main_eval.py:188

↓ 1 callersMethodclose

(self)

env/multiagent_com/rendering.py:342

↓ 1 callersFunctiondata_preprocess

(obs)

network/base_net.py:70

↓ 1 callersMethoddec_to_base

(self, num, base)

env/UAV_env.py:27

↓ 1 callersMethodevaluateStep

(self)

runner.py:105

↓ 1 callersFunctionget_alg_runner

(alg, run_time)

main_eval.py:48

↓ 1 callersFunctionget_data

获取数据

plot_reward_all.py:43

next →1–100 of 307, ranked by callers