LangMARL
0.2.0
Usage
API Reference
LangMARL
Index
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
O
|
P
|
R
|
S
|
T
|
W
A
act() (langmarl.BaseAgent method)
add_usage() (langmarl.TokenTracker method)
aggregate_gradients() (langmarl.BaseOptimizer method)
(langmarl.PolicyGradientOptimizer static method)
apply_gradient() (langmarl.BaseOptimizer method)
(langmarl.PolicyGradientOptimizer static method)
B
BaseAgent (class in langmarl)
BaseConfig (class in langmarl)
BaseCritic (class in langmarl)
BaseEnvironment (class in langmarl)
BaseOptimizer (class in langmarl)
BaseReward (class in langmarl)
C
Callback (class in langmarl)
CentralizedCritic (class in langmarl)
chat() (langmarl.LLMClient method)
chat_with_usage() (langmarl.LLMClient method)
CheckpointCallback (class in langmarl)
collect_trajectory() (langmarl.BaseEnvironment method)
compute() (langmarl.BaseReward method)
count() (langmarl.TrajectoryStore method)
D
debug() (langmarl.RunLogger method)
diff_policies() (langmarl.PolicyCheckpoint method)
E
EarlyStoppingCallback (class in langmarl)
episode_saved() (langmarl.RunLogger method)
error() (langmarl.RunLogger method)
estimate_cost() (langmarl.TokenTracker method)
evaluate() (langmarl.BaseCritic method)
(langmarl.CentralizedCritic method)
evaluation_done() (langmarl.RunLogger method)
F
format_for_credit_assignment() (langmarl.TrajectoryFormatter static method)
format_trajectory() (langmarl.TrajectoryFormatter static method)
format_trajectory_minimal() (langmarl.TrajectoryFormatter static method)
from_dict() (langmarl.LLMConfig class method)
from_json() (langmarl.BaseConfig class method)
from_preset() (langmarl.LLMConfig class method)
G
generate_gradient() (langmarl.BaseOptimizer method)
(langmarl.PolicyGradientOptimizer method)
generate_shared_gradient() (langmarl.PolicyGradientOptimizer method)
get_actor_llm() (langmarl.BaseConfig method)
get_api_key() (langmarl.LLMConfig method)
get_critic_llm() (langmarl.BaseConfig method)
get_llm_config() (in module langmarl)
get_optimizer_llm() (langmarl.BaseConfig method)
get_policies() (langmarl.PolicyCheckpoint method)
get_stats() (langmarl.TokenTracker method)
get_summary_string() (langmarl.TokenTracker method)
gradient_saved() (langmarl.RunLogger method)
I
info() (langmarl.RunLogger method)
iteration_end() (langmarl.RunLogger method)
iteration_start() (langmarl.RunLogger method)
L
langmarl
module
LanguageTaskConfig (class in langmarl)
list_available_models() (in module langmarl)
list_envs() (in module langmarl)
LLMClient (class in langmarl)
LLMConfig (class in langmarl)
load() (langmarl.TrajectoryStore method)
load_config() (in module langmarl)
LocalStore (class in langmarl)
LoggingCallback (class in langmarl)
M
make_env() (in module langmarl)
module
langmarl
MonteCarloTrainer (class in langmarl)
O
on_episode_complete() (langmarl.Callback method)
on_iteration_end() (langmarl.Callback method)
on_iteration_start() (langmarl.Callback method)
on_policy_update() (langmarl.Callback method)
OvercookedConfig (class in langmarl)
P
parse_credit_response() (langmarl.PolicyGradientOptimizer static method)
PistonballConfig (class in langmarl)
PolicyCheckpoint (class in langmarl)
PolicyGradientOptimizer (class in langmarl)
R
raw_client (langmarl.LLMClient attribute)
register_env() (in module langmarl)
reset() (langmarl.BaseEnvironment method)
(langmarl.TokenTracker method)
RunLogger (class in langmarl)
S
save() (langmarl.TrajectoryStore method)
save_policies() (langmarl.PolicyCheckpoint method)
step() (langmarl.BaseEnvironment method)
T
to_dict() (langmarl.LLMConfig method)
to_json() (langmarl.BaseConfig method)
TokenTracker (class in langmarl)
train() (in module langmarl)
(langmarl.MonteCarloTrainer method)
train_one_iteration() (langmarl.MonteCarloTrainer method)
Trajectory (class in langmarl)
TrajectoryFormatter (class in langmarl)
TrajectoryStore (class in langmarl)
W
warning() (langmarl.RunLogger method)