academia
latest
Modules
academia.agents module
academia.environments module
academia.curriculum module
academia.tools module
academia.utils module
Guides
Using your own environments
academia
Index
Edit on GitHub
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
K
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
W
A
academia.agents
module
academia.agents.base
module
academia.curriculum
module
academia.environments
module
academia.environments.base
module
academia.tools
module
academia.tools.visualizations
module
academia.utils
module
academia.utils.models
module
academia.utils.models.bridge_building
module
academia.utils.models.door_key
module
academia.utils.models.lava_crossing
module
academia.utils.models.lunar_lander
module
academia.utils.models.ms_pacman
module
actions (academia.agents.PPOAgent.PPOBuffer attribute)
actions_logits (academia.agents.PPOAgent.PPOBuffer attribute)
actor (academia.agents.PPOAgent attribute)
actor_architecture (academia.agents.PPOAgent attribute)
agent (academia.tools.AgentDebugger attribute)
Agent (class in academia.agents.base)
agent_evaluations (academia.curriculum.LearningStats attribute)
agent_save_path (academia.curriculum.LearningTask attribute)
AgentDebugger (class in academia.tools)
alpha (academia.agents.base.TabularAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
append_step_count (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.base.GenericGymnasiumWrapper attribute)
(academia.environments.base.GenericMiniGridWrapper attribute)
(academia.environments.BridgeBuilding attribute)
(academia.environments.DoorKey attribute)
(academia.environments.LavaCrossing attribute)
(academia.environments.LunarLander attribute)
(academia.environments.MsPacman attribute)
B
batch_size (academia.agents.DQNAgent attribute)
(academia.agents.PPOAgent attribute)
BridgeBuilding (class in academia.environments)
buffer (academia.agents.PPOAgent attribute)
C
calculate_rewards_to_go() (academia.agents.PPOAgent.PPOBuffer method)
clip (academia.agents.PPOAgent attribute)
cpu_lap_times (academia.utils.Stopwatch property)
create_figure() (in module academia.tools.visualizations)
critic (academia.agents.PPOAgent attribute)
critic_architecture (academia.agents.PPOAgent attribute)
Curriculum (class in academia.curriculum)
D
device (academia.agents.DQNAgent attribute)
(academia.agents.PPOAgent attribute)
difficulty (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.base.GenericGymnasiumWrapper attribute)
(academia.environments.base.GenericMiniGridWrapper attribute)
(academia.environments.base.ScalableEnvironment attribute)
(academia.environments.BridgeBuilding attribute)
(academia.environments.DoorKey attribute)
(academia.environments.LavaCrossing attribute)
(academia.environments.LunarLander attribute)
(academia.environments.MsPacman attribute)
discrete (academia.agents.PPOAgent attribute)
DoorKey (class in academia.environments)
DQNAgent (class in academia.agents)
E
entropy_coefficient (academia.agents.PPOAgent attribute)
env (academia.curriculum.LearningTask attribute)
(academia.tools.AgentDebugger attribute)
episode_counter (academia.agents.PPOAgent.PPOBuffer attribute)
episode_cpu_times (academia.curriculum.LearningStats attribute)
episode_length_counter (academia.agents.PPOAgent.PPOBuffer attribute)
episode_lengths (academia.agents.PPOAgent.PPOBuffer attribute)
episode_rewards (academia.curriculum.LearningStats attribute)
episode_rewards_moving_avg (academia.curriculum.LearningStats attribute)
episode_wall_times (academia.curriculum.LearningStats attribute)
episodes (academia.tools.AgentDebugger attribute)
epsilon (academia.agents.base.EpsilonGreedyAgent attribute)
(academia.agents.base.TabularAgent attribute)
(academia.agents.DQNAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
epsilon_decay (academia.agents.base.EpsilonGreedyAgent attribute)
(academia.agents.base.TabularAgent attribute)
(academia.agents.DQNAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
EpsilonGreedyAgent (class in academia.agents.base)
evaluation_interval (academia.curriculum.LearningStats attribute)
experience (academia.agents.DQNAgent attribute)
F
flatten_state (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.MsPacman attribute)
forward() (academia.utils.models.bridge_building.MLPActor method)
(academia.utils.models.bridge_building.MLPCritic method)
(academia.utils.models.bridge_building.MLPDQN method)
(academia.utils.models.bridge_building.MLPStepActor method)
(academia.utils.models.bridge_building.MLPStepCritic method)
(academia.utils.models.bridge_building.MLPStepDQN method)
(academia.utils.models.door_key.MLPActor method)
(academia.utils.models.door_key.MLPCritic method)
(academia.utils.models.door_key.MLPDQN method)
(academia.utils.models.door_key.MLPStepActor method)
(academia.utils.models.door_key.MLPStepCritic method)
(academia.utils.models.door_key.MLPStepDQN method)
(academia.utils.models.lava_crossing.MLPActor method)
(academia.utils.models.lava_crossing.MLPCritic method)
(academia.utils.models.lava_crossing.MLPDQN method)
(academia.utils.models.lava_crossing.MLPStepActor method)
(academia.utils.models.lava_crossing.MLPStepCritic method)
(academia.utils.models.lava_crossing.MLPStepDQN method)
(academia.utils.models.lunar_lander.MLPActor method)
(academia.utils.models.lunar_lander.MLPCritic method)
(academia.utils.models.lunar_lander.MLPDQN method)
(academia.utils.models.lunar_lander.MLPStepActor method)
(academia.utils.models.lunar_lander.MLPStepCritic method)
(academia.utils.models.lunar_lander.MLPStepDQN method)
(academia.utils.models.ms_pacman.MLPActor method)
(academia.utils.models.ms_pacman.MLPCritic method)
(academia.utils.models.ms_pacman.MLPDQN method)
(academia.utils.models.ms_pacman.MLPStepActor method)
(academia.utils.models.ms_pacman.MLPStepCritic method)
(academia.utils.models.ms_pacman.MLPStepDQN method)
from_dict() (academia.curriculum.LearningTask class method)
G
gamma (academia.agents.base.Agent attribute)
(academia.agents.base.EpsilonGreedyAgent attribute)
(academia.agents.base.TabularAgent attribute)
(academia.agents.DQNAgent attribute)
(academia.agents.PPOAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
GenericAtariWrapper (class in academia.environments.base)
GenericGymnasiumWrapper (class in academia.environments.base)
GenericMiniGridWrapper (class in academia.environments.base)
get_action() (academia.agents.base.Agent method)
(academia.agents.base.TabularAgent method)
(academia.agents.DQNAgent method)
(academia.agents.PPOAgent method)
get_aggregate() (academia.curriculum.LearningStatsAggregator method)
get_colors() (in module academia.tools.visualizations)
get_legal_mask() (academia.environments.base.GenericGymnasiumWrapper method)
(academia.environments.base.ScalableEnvironment method)
(academia.environments.BridgeBuilding method)
get_tensors() (academia.agents.PPOAgent.PPOBuffer method)
get_type() (academia.utils.SavableLoadable static method)
get_type_name_full() (academia.utils.SavableLoadable static method)
greedy (academia.tools.AgentDebugger attribute)
I
input_timeout (academia.tools.AgentDebugger attribute)
is_running (academia.utils.Stopwatch property)
K
key_action_map (academia.tools.AgentDebugger attribute)
L
lap() (academia.utils.Stopwatch method)
LavaCrossing (class in academia.environments)
LearningStats (class in academia.curriculum)
LearningStatsAggregator (class in academia.curriculum)
LearningTask (class in academia.curriculum)
load() (academia.agents.base.TabularAgent class method)
(academia.agents.DQNAgent class method)
(academia.agents.PPOAgent class method)
(academia.curriculum.Curriculum class method)
(academia.curriculum.LearningStats class method)
(academia.curriculum.LearningTask class method)
(academia.utils.SavableLoadable class method)
lr (academia.agents.DQNAgent attribute)
(academia.agents.PPOAgent attribute)
LunarLander (class in academia.environments)
M
max_steps (academia.environments.BridgeBuilding attribute)
memory (academia.agents.DQNAgent attribute)
min_epsilon (academia.agents.base.EpsilonGreedyAgent attribute)
(academia.agents.base.TabularAgent attribute)
(academia.agents.DQNAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
MLPActor (class in academia.utils.models.bridge_building)
(class in academia.utils.models.door_key)
(class in academia.utils.models.lava_crossing)
(class in academia.utils.models.lunar_lander)
(class in academia.utils.models.ms_pacman)
MLPCritic (class in academia.utils.models.bridge_building)
(class in academia.utils.models.door_key)
(class in academia.utils.models.lava_crossing)
(class in academia.utils.models.lunar_lander)
(class in academia.utils.models.ms_pacman)
MLPDQN (class in academia.utils.models.bridge_building)
(class in academia.utils.models.door_key)
(class in academia.utils.models.lava_crossing)
(class in academia.utils.models.lunar_lander)
(class in academia.utils.models.ms_pacman)
MLPStepActor (class in academia.utils.models.bridge_building)
(class in academia.utils.models.door_key)
(class in academia.utils.models.lava_crossing)
(class in academia.utils.models.lunar_lander)
(class in academia.utils.models.ms_pacman)
MLPStepCritic (class in academia.utils.models.bridge_building)
(class in academia.utils.models.door_key)
(class in academia.utils.models.lava_crossing)
(class in academia.utils.models.lunar_lander)
(class in academia.utils.models.ms_pacman)
MLPStepDQN (class in academia.utils.models.bridge_building)
(class in academia.utils.models.door_key)
(class in academia.utils.models.lava_crossing)
(class in academia.utils.models.lunar_lander)
(class in academia.utils.models.ms_pacman)
module
academia.agents
academia.agents.base
academia.curriculum
academia.environments
academia.environments.base
academia.tools
academia.tools.visualizations
academia.utils
academia.utils.models
academia.utils.models.bridge_building
academia.utils.models.door_key
academia.utils.models.lava_crossing
academia.utils.models.lunar_lander
academia.utils.models.ms_pacman
MsPacman (class in academia.environments)
N
n_actions (academia.agents.base.Agent attribute)
(academia.agents.base.EpsilonGreedyAgent attribute)
(academia.agents.base.TabularAgent attribute)
(academia.agents.DQNAgent attribute)
(academia.agents.PPOAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
N_ACTIONS (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.base.GenericGymnasiumWrapper attribute)
(academia.environments.base.GenericMiniGridWrapper attribute)
(academia.environments.base.ScalableEnvironment attribute)
(academia.environments.BridgeBuilding attribute)
(academia.environments.DoorKey attribute)
(academia.environments.LavaCrossing attribute)
(academia.environments.LunarLander attribute)
(academia.environments.MsPacman attribute)
n_episodes (academia.agents.PPOAgent.PPOBuffer attribute)
n_epochs (academia.agents.PPOAgent attribute)
n_frames_stacked (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.base.GenericGymnasiumWrapper attribute)
(academia.environments.base.GenericMiniGridWrapper attribute)
(academia.environments.base.ScalableEnvironment attribute)
(academia.environments.BridgeBuilding attribute)
(academia.environments.DoorKey attribute)
(academia.environments.LavaCrossing attribute)
(academia.environments.LunarLander attribute)
(academia.environments.MsPacman attribute)
n_steps (academia.agents.PPOAgent.PPOBuffer attribute)
name (academia.curriculum.LearningTask attribute)
network (academia.agents.DQNAgent attribute)
nn_architecture (academia.agents.DQNAgent attribute)
O
observe() (academia.environments.base.GenericGymnasiumWrapper method)
(academia.environments.base.ScalableEnvironment method)
(academia.environments.BridgeBuilding method)
optimizer (academia.agents.DQNAgent attribute)
output_dir (academia.curriculum.Curriculum attribute)
P
paused (academia.tools.AgentDebugger attribute)
peek_lap_time() (academia.utils.Stopwatch method)
peek_time() (academia.utils.Stopwatch method)
plot_evaluation_impact() (in module academia.tools.visualizations)
plot_evaluation_impact_2d() (in module academia.tools.visualizations)
plot_time_impact() (in module academia.tools.visualizations)
plot_trajectories() (in module academia.tools.visualizations)
PPOAgent (class in academia.agents)
PPOAgent.PPOBuffer (class in academia.agents)
Q
q_table (academia.agents.base.TabularAgent attribute)
(academia.agents.QLAgent attribute)
(academia.agents.SarsaAgent attribute)
QLAgent (class in academia.agents)
R
render() (academia.environments.base.GenericGymnasiumWrapper method)
(academia.environments.base.ScalableEnvironment method)
(academia.environments.BridgeBuilding method)
replay_memory_size (academia.agents.DQNAgent attribute)
reserved_keys (academia.tools.AgentDebugger attribute)
reset() (academia.agents.PPOAgent.PPOBuffer method)
(academia.environments.base.GenericGymnasiumWrapper method)
(academia.environments.base.ScalableEnvironment method)
(academia.environments.BridgeBuilding method)
(academia.environments.MsPacman method)
reset_exploration() (academia.agents.base.Agent method)
(academia.agents.base.EpsilonGreedyAgent method)
(academia.agents.PPOAgent method)
reward_density (academia.environments.BridgeBuilding attribute)
rewards (academia.agents.PPOAgent.PPOBuffer attribute)
rewards_to_go (academia.agents.PPOAgent.PPOBuffer attribute)
river_width (academia.environments.BridgeBuilding attribute)
run() (academia.curriculum.Curriculum method)
(academia.curriculum.LearningTask method)
(academia.tools.AgentDebugger method)
running (academia.tools.AgentDebugger attribute)
S
SarsaAgent (class in academia.agents)
SavableLoadable (class in academia.utils)
save() (academia.agents.base.TabularAgent method)
(academia.agents.DQNAgent method)
(academia.agents.PPOAgent method)
(academia.curriculum.Curriculum method)
(academia.curriculum.LearningStats method)
(academia.curriculum.LearningTask method)
(academia.utils.SavableLoadable method)
ScalableEnvironment (class in academia.environments.base)
skip_game_start (academia.environments.MsPacman attribute)
start() (academia.utils.Stopwatch method)
STATE_SHAPE (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.base.GenericGymnasiumWrapper attribute)
(academia.environments.base.GenericMiniGridWrapper attribute)
(academia.environments.base.ScalableEnvironment attribute)
(academia.environments.BridgeBuilding attribute)
(academia.environments.DoorKey attribute)
(academia.environments.LavaCrossing attribute)
(academia.environments.MsPacman attribute)
states (academia.agents.PPOAgent.PPOBuffer attribute)
stats (academia.curriculum.Curriculum property)
(academia.curriculum.LearningStatsAggregator attribute)
(academia.curriculum.LearningTask attribute)
stats_save_path (academia.curriculum.LearningTask attribute)
step() (academia.environments.base.GenericGymnasiumWrapper method)
(academia.environments.base.ScalableEnvironment method)
(academia.environments.BridgeBuilding method)
step_count (academia.environments.base.GenericAtariWrapper attribute)
(academia.environments.base.GenericGymnasiumWrapper attribute)
(academia.environments.base.GenericMiniGridWrapper attribute)
(academia.environments.BridgeBuilding attribute)
(academia.environments.DoorKey attribute)
(academia.environments.LavaCrossing attribute)
(academia.environments.LunarLander attribute)
(academia.environments.MsPacman attribute)
step_counts (academia.curriculum.LearningStats attribute)
step_counts_moving_avg (academia.curriculum.LearningStats attribute)
steps (academia.tools.AgentDebugger attribute)
steps_counter (academia.agents.PPOAgent.PPOBuffer attribute)
stop() (academia.utils.Stopwatch method)
stop_predicates (academia.curriculum.LearningTask attribute)
Stopwatch (class in academia.utils)
T
TabularAgent (class in academia.agents.base)
target_network (academia.agents.DQNAgent attribute)
tasks (academia.curriculum.Curriculum attribute)
tau (academia.agents.DQNAgent attribute)
thoughts_handlers (academia.tools.AgentDebugger attribute)
to_dict() (academia.curriculum.LearningTask method)
train_step (academia.agents.DQNAgent attribute)
training (academia.utils.models.bridge_building.MLPActor attribute)
(academia.utils.models.bridge_building.MLPCritic attribute)
(academia.utils.models.bridge_building.MLPDQN attribute)
(academia.utils.models.bridge_building.MLPStepActor attribute)
(academia.utils.models.bridge_building.MLPStepCritic attribute)
(academia.utils.models.bridge_building.MLPStepDQN attribute)
(academia.utils.models.door_key.MLPActor attribute)
(academia.utils.models.door_key.MLPCritic attribute)
(academia.utils.models.door_key.MLPDQN attribute)
(academia.utils.models.door_key.MLPStepActor attribute)
(academia.utils.models.door_key.MLPStepCritic attribute)
(academia.utils.models.door_key.MLPStepDQN attribute)
(academia.utils.models.lava_crossing.MLPActor attribute)
(academia.utils.models.lava_crossing.MLPCritic attribute)
(academia.utils.models.lava_crossing.MLPDQN attribute)
(academia.utils.models.lava_crossing.MLPStepActor attribute)
(academia.utils.models.lava_crossing.MLPStepCritic attribute)
(academia.utils.models.lava_crossing.MLPStepDQN attribute)
(academia.utils.models.lunar_lander.MLPActor attribute)
(academia.utils.models.lunar_lander.MLPCritic attribute)
(academia.utils.models.lunar_lander.MLPDQN attribute)
(academia.utils.models.lunar_lander.MLPStepActor attribute)
(academia.utils.models.lunar_lander.MLPStepCritic attribute)
(academia.utils.models.lunar_lander.MLPStepDQN attribute)
(academia.utils.models.ms_pacman.MLPActor attribute)
(academia.utils.models.ms_pacman.MLPCritic attribute)
(academia.utils.models.ms_pacman.MLPDQN attribute)
(academia.utils.models.ms_pacman.MLPStepActor attribute)
(academia.utils.models.ms_pacman.MLPStepCritic attribute)
(academia.utils.models.ms_pacman.MLPStepDQN attribute)
U
update() (academia.agents.base.Agent method)
(academia.agents.DQNAgent method)
(academia.agents.PPOAgent method)
(academia.agents.PPOAgent.PPOBuffer method)
(academia.agents.QLAgent method)
(academia.agents.SarsaAgent method)
(academia.curriculum.LearningStats method)
update_every (academia.agents.DQNAgent attribute)
update_exploration() (academia.agents.base.Agent method)
(academia.agents.base.EpsilonGreedyAgent method)
(academia.agents.PPOAgent method)
W
wall_lap_times (academia.utils.Stopwatch property)
Read the Docs
v: latest
Versions
latest
stable
v0.1.0
Downloads
On Read the Docs
Project Home
Builds