MCPcopy Create free account

hub / github.com/NeuralMMO/baselines / functions

Functions176 in github.com/NeuralMMO/baselines

Method__init__
(self, input_size, hidden_size)
agent_zoo/takeru/policy.py:118
Method__init__
(self, input_size, hidden_size)
agent_zoo/takeru/policy.py:216
Method__init__
(self, input_size, hidden_size)
agent_zoo/takeru/policy.py:262
Method__init__
(self, input_size, hidden_size)
agent_zoo/takeru/policy.py:273
Method__init__
(self, input_size, hidden_size, task_size)
agent_zoo/takeru/policy.py:282
Method__init__
(self, input_size, hidden_size)
agent_zoo/takeru/policy.py:291
Method__init__
( # BaseStatWrapper args self, env, eval_mode=False, early_stop_agent_
agent_zoo/takeru/reward_wrapper.py:5
Method__init__
Initialize the TaskEncoder. Args: checkpoint: Path to the pretrained model. context: Python module context in which
curriculum_generation/task_encoder.py:27
Method__init__
(self, task_spec: List[ts.TaskSpec], average_window=50)
curriculum_generation/task_sampler.py:9
Method_create_testing_task_list
Manually generate a list of tasks used for testing.
syllabus_wrapper.py:209
Method_debug
(self, agents)
agent_zoo/takeru/policy.py:209
Methodaction
Called before actions are passed from the model to the environment
agent_zoo/neurips23_start_kit/reward_wrapper.py:56
Methodaction_space
Implement Neural MMO's action_space method.
syllabus_wrapper.py:163
Methodadd_tasks
(self, task_spec: List[ts.TaskSpec])
curriculum_generation/task_sampler.py:18
Functionagent_creator
(env, args)
train.py:67
Functionagent_creator
(env, args=None)
evaluate.py:102
Methodagents
(self)
reinforcement_learning/stat_wrapper.py:45
Functionclose
(data)
reinforcement_learning/clean_pufferl.py:562
Functioncreate
( self: object = None, config: pufferlib.namespace = None, exp_name: str = None, track: bool =
reinforcement_learning/clean_pufferl.py:68
Methodcreate_manual_task_list
(self)
syllabus_wrapper.py:179
Methodcreate_original_task_list
(self)
syllabus_wrapper.py:167
Methoddecode_actions
(self, hidden, lookup)
agent_zoo/neurips23_start_kit/baseline_policy.py:79
Methoddecode_actions
(self, hidden, lookup)
agent_zoo/yaofeng/policy.py:68
Methoddecode_actions
(self, hidden, lookup)
agent_zoo/takeru/policy.py:74
Methodencode_observations
(self, flat_observations)
agent_zoo/neurips23_start_kit/baseline_policy.py:40
Methodencode_observations
(self, flat_observations)
agent_zoo/yaofeng/policy.py:41
Methodencode_observations
(self, flat_observations)
agent_zoo/takeru/policy.py:39
Functionenv_creator
(*args, **kwargs)
evaluate.py:81
Functionenv_creator
Create an environment.
reinforcement_learning/environment.py:55
Functionevaluate
(data)
reinforcement_learning/clean_pufferl.py:254
Methodforward
(self, tile)
agent_zoo/neurips23_start_kit/baseline_policy.py:95
Methodforward
(self, agents, my_id)
agent_zoo/neurips23_start_kit/baseline_policy.py:123
Methodforward
(self, items)
agent_zoo/neurips23_start_kit/baseline_policy.py:157
Methodforward
(self, inventory)
agent_zoo/neurips23_start_kit/baseline_policy.py:178
Methodforward
(self, market)
agent_zoo/neurips23_start_kit/baseline_policy.py:189
Methodforward
(self, task)
agent_zoo/neurips23_start_kit/baseline_policy.py:198
Methodforward
(self, hidden, lookup)
agent_zoo/neurips23_start_kit/baseline_policy.py:232
Methodforward
(self, x)
agent_zoo/yaofeng/policy.py:85
Methodforward
(self, tile)
agent_zoo/yaofeng/policy.py:103
Methodforward
(self, x)
agent_zoo/yaofeng/policy.py:133
Methodforward
(self, agents, my_id)
agent_zoo/yaofeng/policy.py:163
Methodforward
(self, items)
agent_zoo/yaofeng/policy.py:214
Methodforward
(self, inventory)
agent_zoo/yaofeng/policy.py:239
Methodforward
(self, market)
agent_zoo/yaofeng/policy.py:252
Methodforward
(self, task)
agent_zoo/yaofeng/policy.py:263
Methodforward
(self, hidden, lookup)
agent_zoo/yaofeng/policy.py:298
Methodforward
(self, tile)
agent_zoo/takeru/policy.py:94
Methodforward
(self, agents, my_id)
agent_zoo/takeru/policy.py:173
Methodforward
(self, items)
agent_zoo/takeru/policy.py:243
Methodforward
(self, inventory)
agent_zoo/takeru/policy.py:266
Methodforward
(self, market)
agent_zoo/takeru/policy.py:277
Methodforward
(self, task)
agent_zoo/takeru/policy.py:286
Methodforward
(self, hidden, lookup)
agent_zoo/takeru/policy.py:351
Functionmain
()
train_helper.py:75
Functionmake_env_creator
( reward_wrapper_cls: BaseParallelWrapper, syllabus_wrapper=False, syllabus=None )
reinforcement_learning/environment.py:52
Functionmake_syllabus_env_creator
(args, agent_module)
syllabus_wrapper.py:20
Methodobservation
Called before observations are returned from the environment Use this to define custom featurizers. Changing the space itself requires you to
agent_zoo/neurips23_start_kit/reward_wrapper.py:46
Methodobservation
Called before observations are returned from the environment Use this to define custom featurizers. Changing the space itself requires you to
agent_zoo/yaofeng/reward_wrapper.py:65
Methodreset
Called at the start of each episode
reinforcement_learning/stat_wrapper.py:48
Methodreset
Called at the start of each episode
agent_zoo/neurips23_start_kit/reward_wrapper.py:25
Methodreset
Called at the start of each episode
agent_zoo/yaofeng/reward_wrapper.py:48
Methodreset
(self)
curriculum_generation/task_sampler.py:15
Methodreward_terminated_truncated_info
(self, agent_id, reward, terminated, truncated, info)
agent_zoo/neurips23_start_kit/reward_wrapper.py:63
Methodreward_terminated_truncated_info
(self, agent_id, reward, terminated, truncated, info)
agent_zoo/yaofeng/reward_wrapper.py:84
Methodreward_terminated_truncated_info
(self, agent_id, reward, terminated, truncated, info)
agent_zoo/takeru/reward_wrapper.py:39
Methodsample_tasks
( self, num_tasks, random_ratio=0.5, reset_sampling_weight=True, )
curriculum_generation/task_sampler.py:66
MethodsetUpClass
(cls)
tests/test_task_encoder.py:16
Methodset_debug
(self, debug)
evaluate.py:116
Methodstep
(self, action)
syllabus_wrapper.py:158
MethodtearDownClass
(cls)
tests/test_task_encoder.py:22
Methodtest_contruct_prompt
(self)
tests/test_task_encoder.py:48
Methodtest_embed_dim
(self)
tests/test_task_encoder.py:25
Methodtest_get_task_deps_src
(self)
tests/test_task_encoder.py:36
Methodtest_task_encoder_api
(self)
tests/test_task_encoder.py:28
Functiontrain
(data)
reinforcement_learning/clean_pufferl.py:399
Methodupdate_context
Update the module context, extracting function dictionary.
curriculum_generation/task_encoder.py:62
← previous101–176 of 176, ranked by callers