AMLGym: benchmarking action model learning.
Overview
Getting started
Passive Algorithms
SAM
OffLAM
NOLAM
ROSAME
Active Algorithms
Random Agent
Information Gain Agent
OLAM
Metrics
Syntactic similarity
Problem solving
Predictive power
Tutorials
Learning Domain Models
1. Benchmark domains and trajectories
2. Passive Algorithms
3. Active Algorithms
Evaluating Domain Models
1. Syntactic similarity metrics
2. Problem solving metrics
3. Predictive power metrics
Tutorial AAAI 2026
Tutorial AAMAS 2026
API
amlgym
amlgym package
amlgym.algorithms package
amlgym.benchmarks package
amlgym.metrics package
amlgym.modeling package
amlgym.util package
AMLGym: benchmarking action model learning.
Index
Index
_
|
A
|
C
|
E
|
F
|
G
|
I
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
|
U
|
V
|
W
_
__init__() (amlgym.modeling.UPEnv.UPEnv method)
A
actions (amlgym.modeling.trajectory.Trajectory attribute)
ActiveAlgorithmAdapter (class in amlgym.algorithms.ActiveAlgorithmAdapter)
amlgym
module
amlgym.algorithms
module
amlgym.algorithms.ActiveAlgorithmAdapter
module
amlgym.algorithms.InformationGainAgent
module
amlgym.algorithms.NOLAM
module
amlgym.algorithms.OffLAM
module
amlgym.algorithms.OLAM
module
amlgym.algorithms.PassiveAlgorithmAdapter
module
amlgym.algorithms.RandomAgent
module
amlgym.algorithms.ROSAME
module
amlgym.algorithms.SAM
module
amlgym.benchmarks
module
amlgym.metrics
module
amlgym.metrics._predictive
module
amlgym.metrics._solving
module
amlgym.metrics._syntactic
module
amlgym.modeling
module
amlgym.modeling.env
module
amlgym.modeling.trajectory
module
amlgym.modeling.UPEnv
module
amlgym.util
module
amlgym.util.gen_problems
module
amlgym.util.gen_probs_solving
module
amlgym.util.gen_states_predictability
module
amlgym.util.gen_trajs_learning
module
amlgym.util.gen_trajs_learning_hard
module
amlgym.util.gen_trajs_predictability
module
amlgym.util.SimpleDomainReader
module
amlgym.util.util
module
applicability() (in module amlgym.metrics)
(in module amlgym.metrics._predictive)
applicable_actions() (amlgym.modeling.env.Env method)
(amlgym.modeling.UPEnv.UPEnv method)
apply() (amlgym.modeling.env.Env method)
(amlgym.modeling.UPEnv.UPEnv method)
C
clean_pddl_domain_file() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
compare_trajs() (in module amlgym.util.util)
E
empty() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
empty_domain() (in module amlgym.util.util)
Env (class in amlgym.modeling.env)
epsilon (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
F
fix_domain_format() (in module amlgym.util.util)
G
generate_traj() (in module amlgym.util.gen_states_predictability)
(in module amlgym.util.gen_trajs_learning)
(in module amlgym.util.gen_trajs_learning_hard)
(in module amlgym.util.gen_trajs_predictability)
get_algorithm() (in module amlgym.algorithms)
get_applicable_actions_val() (in module amlgym.util.util)
get_domain() (in module amlgym.benchmarks)
get_domain_names() (in module amlgym.benchmarks)
get_domain_path() (in module amlgym.benchmarks)
get_op_relevant_predicates() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
get_problems_path() (in module amlgym.benchmarks)
get_test_states() (in module amlgym.benchmarks)
get_trajectories() (in module amlgym.benchmarks)
get_trajectories_path() (in module amlgym.benchmarks)
ground_actions (amlgym.modeling.UPEnv.UPEnv property)
I
InformationGainAgent (class in amlgym.algorithms.InformationGainAgent)
init_prec_eff() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
input_domain_path (amlgym.algorithms.ActiveAlgorithmAdapter.ActiveAlgorithmAdapter attribute)
(amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
(amlgym.algorithms.OLAM.OLAM attribute)
(amlgym.algorithms.RandomAgent.RandomAgent attribute)
L
learn() (amlgym.algorithms.ActiveAlgorithmAdapter.ActiveAlgorithmAdapter method)
(amlgym.algorithms.InformationGainAgent.InformationGainAgent method)
(amlgym.algorithms.NOLAM.NOLAM method)
(amlgym.algorithms.OffLAM.OffLAM method)
(amlgym.algorithms.OLAM.OLAM method)
(amlgym.algorithms.PassiveAlgorithmAdapter.PassiveAlgorithmAdapter method)
(amlgym.algorithms.RandomAgent.RandomAgent method)
(amlgym.algorithms.ROSAME.ROSAME method)
(amlgym.algorithms.SAM.SAM method)
learn_negative_preconditions (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
lookahead_depth (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
lookahead_discount (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
lookahead_top_k (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
M
max_goals (amlgym.algorithms.OLAM.OLAM attribute)
max_length (amlgym.algorithms.OLAM.OLAM attribute)
max_subproblems (amlgym.algorithms.OLAM.OLAM attribute)
mcts_iterations (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
mcts_rollout_depth (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
model_mode (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
module
amlgym
amlgym.algorithms
amlgym.algorithms.ActiveAlgorithmAdapter
amlgym.algorithms.InformationGainAgent
amlgym.algorithms.NOLAM
amlgym.algorithms.OffLAM
amlgym.algorithms.OLAM
amlgym.algorithms.PassiveAlgorithmAdapter
amlgym.algorithms.RandomAgent
amlgym.algorithms.ROSAME
amlgym.algorithms.SAM
amlgym.benchmarks
amlgym.metrics
amlgym.metrics._predictive
amlgym.metrics._solving
amlgym.metrics._syntactic
amlgym.modeling
amlgym.modeling.env
amlgym.modeling.trajectory
amlgym.modeling.UPEnv
amlgym.util
amlgym.util.gen_problems
amlgym.util.gen_probs_solving
amlgym.util.gen_states_predictability
amlgym.util.gen_trajs_learning
amlgym.util.gen_trajs_learning_hard
amlgym.util.gen_trajs_predictability
amlgym.util.SimpleDomainReader
amlgym.util.util
N
noise (amlgym.algorithms.NOLAM.NOLAM attribute)
NOLAM (class in amlgym.algorithms.NOLAM)
O
OffLAM (class in amlgym.algorithms.OffLAM)
OLAM (class in amlgym.algorithms.OLAM)
Operator (class in amlgym.util.SimpleDomainReader)
P
PassiveAlgorithmAdapter (class in amlgym.algorithms.PassiveAlgorithmAdapter)
planning_timeout (amlgym.algorithms.OLAM.OLAM attribute)
predicted_effects() (in module amlgym.metrics)
(in module amlgym.metrics._predictive)
predictive_power() (in module amlgym.metrics)
(in module amlgym.metrics._predictive)
preprocess_trace() (in module amlgym.util.util)
print_actions_with_no_effs() (in module amlgym.util.util)
print_algorithms() (in module amlgym.algorithms)
print_domains() (in module amlgym.benchmarks)
print_metrics() (in module amlgym.metrics)
problem (amlgym.modeling.UPEnv.UPEnv attribute)
problem_barman() (in module amlgym.util.gen_problems)
problem_blocksworld() (in module amlgym.util.gen_problems)
problem_childsnack() (in module amlgym.util.gen_problems)
problem_depots() (in module amlgym.util.gen_problems)
problem_driverlog() (in module amlgym.util.gen_problems)
problem_elevators() (in module amlgym.util.gen_problems)
problem_ferry() (in module amlgym.util.gen_problems)
problem_floortile() (in module amlgym.util.gen_problems)
problem_goldminer() (in module amlgym.util.gen_problems)
problem_grid() (in module amlgym.util.gen_problems)
problem_grippers() (in module amlgym.util.gen_problems)
problem_hanoi() (in module amlgym.util.gen_problems)
problem_matchingbw() (in module amlgym.util.gen_problems)
problem_miconic() (in module amlgym.util.gen_problems)
problem_nomystery() (in module amlgym.util.gen_problems)
problem_npuzzle() (in module amlgym.util.gen_problems)
problem_parking() (in module amlgym.util.gen_problems)
problem_rovers() (in module amlgym.util.gen_problems)
problem_satellite() (in module amlgym.util.gen_problems)
problem_sokoban() (in module amlgym.util.gen_problems)
problem_solving() (in module amlgym.metrics)
(in module amlgym.metrics._solving)
problem_spanner() (in module amlgym.util.gen_problems)
problem_tpp() (in module amlgym.util.gen_problems)
problem_transport() (in module amlgym.util.gen_problems)
problem_visitall() (in module amlgym.util.gen_problems)
problem_zenotravel() (in module amlgym.util.gen_problems)
R
RandomAgent (class in amlgym.algorithms.RandomAgent)
read() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
read_object_types_hierarchy() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
read_operators() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
read_predicates() (amlgym.util.SimpleDomainReader.SimpleDomainReader method)
reduce_problem_settings() (in module amlgym.util.util)
remove_trajs() (in module amlgym.util.util)
replan() (in module amlgym.util.gen_states_predictability)
(in module amlgym.util.gen_trajs_learning)
(in module amlgym.util.gen_trajs_learning_hard)
(in module amlgym.util.gen_trajs_predictability)
ROSAME (class in amlgym.algorithms.ROSAME)
S
SAM (class in amlgym.algorithms.SAM)
selection_strategy (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
SimpleDomainReader (class in amlgym.util.SimpleDomainReader)
spare_objects_per_type (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
states (amlgym.modeling.trajectory.Trajectory attribute)
syntactic_precision() (in module amlgym.metrics)
(in module amlgym.metrics._syntactic)
syntactic_recall() (in module amlgym.metrics)
(in module amlgym.metrics._syntactic)
T
temperature (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
Trajectory (class in amlgym.modeling.trajectory)
U
UPEnv (class in amlgym.modeling.UPEnv)
use_object_subset (amlgym.algorithms.InformationGainAgent.InformationGainAgent attribute)
V
validate_plan() (in module amlgym.metrics._solving)
W
write() (amlgym.modeling.trajectory.Trajectory method)
(amlgym.util.SimpleDomainReader.SimpleDomainReader method)