Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/EMI-Group/evorl
/ functions
Functions
1,203 in github.com/EMI-Group/evorl
⨍
Functions
1,203
◇
Types & classes
249
↳
Endpoints
1
Method
_tell_with_rl_injection
(ec_opt_state, fitnesses)
evorl/algorithms/erl/erl_td3/erl_ga.py:256
Function
_terminate_cond
(carry)
evorl/rollout.py:227
Function
_terminate_cond
(carry)
evorl/evaluators/mo_brax_evaluator.py:262
Function
_terminate_cond
(carry)
tests/test_evaluator.py:53
Method
_train_steps
(pop_wf_state)
evorl/algorithms/meta/pbt_workflow.py:215
Method
_train_steps
(pop_wf_state, replay_buffer_state)
evorl/algorithms/meta/pbt_workflow.py:583
Method
_update_actor
(carry)
evorl/algorithms/td7.py:717
Method
_update_actor_fn
(agent_state, opt_state, sample_batch, key)
evorl/algorithms/contrib/td3_v2.py:123
Method
_update_actor_fn
(agent_state, opt_state, sample_batch, key)
evorl/algorithms/contrib/td3_v3.py:405
Method
_update_checkpoint
(ag_state)
evorl/algorithms/td7.py:836
Function
_update_critic_fn
(carry, sample_batch)
evorl/algorithms/contrib/pop_episodic_td3.py:356
Function
_update_critic_fn
(carry, sample_batch)
evorl/algorithms/erl/cemrl_td3/cemrl_td3_workflow.py:247
Function
_update_critic_fn
(carry, sample_batch)
evorl/algorithms/erl/erl_td3/erl_td3_workflow.py:353
Function
_update_critic_fn
(carry, sample_batch)
evorl/algorithms/erl/erl_td3/erl_eda.py:495
Method
_update_critic_fn
(agent_state, opt_state, sample_batch, key)
evorl/algorithms/contrib/td3_v2.py:107
Method
_update_critic_fn
(agent_state, opt_state, sample_batch, key)
evorl/algorithms/contrib/td3_v3.py:319
Function
_update_fn
(agent_state, opt_state, sample_batches, key)
evorl/algorithms/contrib/td3_onpolicy.py:326
Function
_update_fn
(agent_state, opt_state, sample_batches, key)
evorl/algorithms/contrib/pop_episodic_td3.py:345
Function
_update_fn
(agent_state, opt_state, sample_batches, key)
evorl/algorithms/erl/cemrl_td3/cemrl_td3_workflow.py:236
Function
_update_fn
(agent_state, opt_state, sample_batches, key)
evorl/algorithms/erl/erl_td3/erl_td3_workflow.py:342
Function
_update_fn
(agent_state, opt_state, sample_batches, key)
evorl/algorithms/erl/erl_td3/erl_eda.py:484
Method
_update_obs_preprocessor
(agent_state, trajectory)
evorl/algorithms/offpolicy_utils.py:124
Method
_update_obs_preprocessor
( self, agent_state: AgentState, trajectory: SampleBatch )
evorl/algorithms/contrib/ars_linear.py:223
Method
_update_obs_preprocessor
(agent_state, trajectory)
evorl/algorithms/contrib/pop_td3.py:141
Method
_update_obs_preprocessor
( self, agent_state: AgentState, trajectory: SampleBatch )
evorl/algorithms/ec/so/ars.py:162
Method
_warmup_step
(state, unused_t)
evorl/algorithms/erl/erl_td3/erl_td3_workflow.py:55
Method
_wf_step_wrapper
(wf_state)
evorl/algorithms/meta/pbt_workflow.py:587
Method
_where_autoreset
(x, y)
evorl/envs/wrappers/training_wrapper.py:339
Method
action_space
(self)
evorl/envs/jumanji.py:44
Method
action_space
(self)
evorl/envs/gymnax.py:78
Method
action_space
(self)
evorl/envs/mujoco_playground.py:95
Method
action_space
(self)
evorl/envs/brax.py:63
Method
action_space
(self)
evorl/envs/envpool.py:180
Method
action_space
(self)
evorl/envs/gymnasium.py:250
Method
action_space
Get the action space of the environment.
evorl/envs/env.py:60
Method
action_space
Return the action space of the environment.
evorl/envs/multi_agent_env.py:27
Method
action_space
(self)
evorl/envs/wrappers/wrapper.py:30
Method
action_space
(self)
evorl/envs/wrappers/action_wrapper.py:30
Method
action_space
(self)
tests/utils.py:55
Method
action_space
(self)
tests/utils.py:102
Method
actor_loss
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/sac.py:314
Function
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/contrib/td3_onpolicy.py:297
Function
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/contrib/pop_episodic_td3.py:313
Function
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/erl/cemrl_td3/cemrl_td3_workflow.py:204
Function
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/erl/erl_td3/erl_td3_workflow.py:312
Function
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/erl/erl_td3/erl_eda.py:455
Method
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/ddpg.py:338
Method
actor_loss_fn
(params, agent_state, sample_batch, key)
evorl/algorithms/td7.py:630
Method
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/td3.py:402
Method
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/sac.py:570
Method
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/contrib/pop_td3.py:259
Method
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/contrib/td3_v2.py:79
Method
actor_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/meta/pbt_sac/param_sac.py:272
Method
add
Add data to the replay buffer. Args: buffer_state: The current state of the replay buffer. xs: The data to add to the
evorl/replay_buffers/replay_buffer.py:42
Method
add
( self, buffer_state: PrioritizedReplayBufferState, xs: chex.ArrayTree, mask:
evorl/replay_buffers/prioritized_replay_buffer.py:59
Function
agent_init_fn
(rng)
evorl/networks/cnn/atari_cnn.py:115
Method
agents
(self)
evorl/envs/jaxmarl.py:96
Method
agents
(self)
evorl/envs/multi_agent_env.py:39
Method
all_steps
(self, read: bool = False)
evorl/utils/orbax_utils.py:85
Method
alpha_loss
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/sac.py:294
Method
alpha_loss_fn
(agent_state, sample_batch, key)
evorl/algorithms/sac.py:576
Method
apply_hyperparams_to_workflow_state
( self, workflow_state: State, hyperparams: PyTreeDict[str, chex.Numeric] )
evorl/algorithms/meta/pbt_workflow.py:347
Method
apply_hyperparams_to_workflow_state
( self, workflow_state: State, hyperparams: PyTreeDict[str, chex.Numeric] )
evorl/algorithms/meta/pbt.py:38
Method
apply_hyperparams_to_workflow_state
( self, workflow_state: State, hyperparams: PyTreeDict[str, chex.Numeric] )
evorl/algorithms/meta/pbt_openes/pbt_param_openes.py:39
Method
apply_hyperparams_to_workflow_state
( self, workflow_state: State, hyperparams: PyTreeDict[str, chex.Numeric] )
evorl/algorithms/meta/pbt_ppo/pbt_param_ppo.py:48
Method
apply_hyperparams_to_workflow_state
( self, workflow_state: State, hyperparams: PyTreeDict[str, chex.Numeric] )
evorl/algorithms/meta/pbt_sac/pbt_param_sac.py:39
Method
ask
(self, state)
evorl/ec/evox_algorithm/cmaes.py:139
Method
ask
(self, state)
evorl/ec/evox_algorithm/cmaes.py:247
Method
ask
(self, state)
evorl/ec/evox_algorithm/openes.py:79
Method
ask
(self, state)
evorl/ec/evox_algorithm/cso.py:70
Method
ask
(self, state: VanillaESState)
evorl/ec/optimizers/vanilla_es.py:47
Method
ask
(self, state: EvoXAlgoState)
evorl/ec/optimizers/evox_wrapper.py:43
Method
ask
(self, state: SepCEMState)
evorl/ec/optimizers/cem.py:62
Method
ask
(self, state: VanillaGAState)
evorl/ec/optimizers/vanilla_ga.py:62
Method
ask
Generate new candidate solutions.
evorl/ec/optimizers/openes.py:77
Method
ask
Generate new candidate solutions.
evorl/ec/optimizers/openes.py:197
Method
ask
(self, state: ERLGAState)
evorl/ec/optimizers/erl_ga.py:63
Method
ask
Generate new candidate solutions.
evorl/ec/optimizers/ec_optimizer.py:21
Function
batchify
Batchify the data for multi-agent training. Output batched data. Args: x: data from each agent, [batch_dims..., val] Not
evorl/utils/ma_utils.py:8
Method
best_step
(self)
evorl/utils/orbax_utils.py:91
Method
build_from_config
Build the rl workflow instance from the config. Args: config: Config of the workflow. enable_multi_devices: Whether m
evorl/workflows/rl_workflow.py:43
Method
build_from_config
Build the ec workflow instance from the config. Args: config: Config of the workflow enable_multi_devices: Whether mu
evorl/workflows/ec_workflow.py:61
Method
build_from_config
( cls, config: DictConfig, enable_multi_devices: bool = False, enable_jit: boo
evorl/algorithms/contrib/pop_td3.py:48
Method
build_from_config
( cls, config: DictConfig, enable_multi_devices: bool = False, enable_jit: boo
evorl/algorithms/contrib/pop_ppo.py:27
Method
build_from_config
( cls, config: DictConfig, enable_multi_devices: bool = False, enable_jit: boo
evorl/algorithms/erl/erl_workflow.py:77
Method
build_from_config
( cls, config: DictConfig, enable_multi_devices: bool = False, enable_jit: boo
evorl/algorithms/erl/cemrl_workflow.py:68
Method
can_sample
Check if the current replay buffer state can be used to sample. Args: buffer_state: The current state of the replay buffer.
evorl/replay_buffers/replay_buffer.py:72
Method
can_sample
(self, buffer_state: ReplayBufferState)
evorl/replay_buffers/replay_buffer.py:119
Method
check_for_errors
(self)
evorl/utils/orbax_utils.py:118
Method
close
(self)
evorl/utils/orbax_utils.py:127
Method
close
(self)
evorl/recorders/recorder.py:47
Method
close
(self)
evorl/recorders/wandb_recorder.py:33
Method
close
(self)
evorl/recorders/log_recorder.py:49
Function
clz_from_iterable
(meta, data)
evorl/types.py:225
Method
compute_actions
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/ddpg.py:104
Method
compute_actions
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/impala.py:99
Method
compute_actions
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/a2c.py:92
Method
compute_actions
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/td7.py:236
Method
compute_actions
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/td3.py:107
Method
compute_actions
( self, agent_state: AgentState, sample_batch: SampleBatch, key: chex.PRNGKey )
evorl/algorithms/sac.py:105
← previous
next →
701–800 of 1,203, ranked by callers