pandemonium
Spinning Up
Spinning Up
Reference
Library Reference
Architectures
Architectures
Benchmarks
Benchmarks
pandemonium
Docs
»
Index
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
Λ
|
Μ
|
Φ
_
__call__() (AccumulatingTrace method)
(CombinedCumulant method)
(ConstantContinuation method)
(ContinuationFunction method)
(Cumulant method)
(Curiosity method)
(DiffContinuation method)
(DutchTrace method)
(EligibilityTrace method)
(FeatureCumulant method)
(Fitness method)
(PixelChange method)
(Policy method)
(SigmoidContinuation method)
A
AC (class in pandemonium.implementations)
AccumulatingTrace (class in pandemonium.traces)
act() (Egreedy method)
(HierarchicalPolicy method)
(Policy method)
(SoftmaxPolicy method)
action_filter() (Policy method)
add() (ER method)
(PER method)
(SegmentedER method)
(SkewedER method)
add_batch() (ER method)
Agent (class in pandemonium.agent)
avf (Demon attribute)
B
BaseNetwork (class in pandemonium.networks)
behavior_policy() (ControlDemon method)
(Demon method)
(TDControl method)
C
capacity (ER attribute)
CategoricalQ (class in pandemonium.demons)
CombinedCumulant (class in pandemonium.cumulants)
ConstantContinuation (class in pandemonium.continuations)
continuation() (GVF method)
ContinuationFunction (class in pandemonium.continuations)
Continuous (class in pandemonium.policies)
ControlDemon (class in pandemonium.demons)
conv2d_size_out() (in module pandemonium.networks)
ConvBody (class in pandemonium.networks)
ConvLSTM (class in pandemonium.networks)
create_horde() (in module pandemonium.implementations)
Cumulant (class in pandemonium.cumulants)
cumulant() (GVF method)
Curiosity (class in pandemonium.implementations)
D
deconv2d_size_out() (in module pandemonium.networks)
delta() (Demon method)
(DiffPolicy method)
(DoubleQLearning method)
(ICM method)
(OfflineTD method)
(OfflineTDControl method)
(OfflineTDPrediction method)
(OnlineTD method)
(OnlineTDControl method)
(OnlineTDPrediction method)
(RewardPrediction method)
(VPG method)
Demon (class in pandemonium.demons)
DiffContinuation (class in pandemonium.continuations)
DiffPolicy (class in pandemonium.policies)
Discrete (class in pandemonium.policies)
dist() (DiffContinuation method)
(DiffPolicy method)
(Discrete method)
(Egreedy method)
(HierarchicalPolicy method)
(Policy method)
(Random method)
(SigmoidContinuation method)
(SoftmaxPolicy method)
(VPG method)
DoubleQLearning (class in pandemonium.implementations)
DQN (class in pandemonium.implementations)
DuellingMixin (class in pandemonium.demons)
DutchTrace (class in pandemonium.traces)
E
Egreedy (class in pandemonium.policies)
EgreedyOverOptions (class in pandemonium.policies)
eligibility() (Demon method)
EligibilityTrace (class in pandemonium.traces)
Empowerment (class in pandemonium.cumulants)
epsilon (Egreedy attribute)
ER (class in pandemonium.experience)
F
FCBody (class in pandemonium.networks)
feature() (Demon method)
feature_dim (BaseNetwork attribute)
FeatureCumulant (class in pandemonium.cumulants)
Fitness (class in pandemonium.cumulants)
forward() (ConvBody method)
(ConvLSTM method)
(FCBody method)
(ForwardModel method)
(Identity method)
(InverseModel method)
(LinearNet method)
(NatureCNN method)
(ParametricDemon method)
(Reshape method)
ForwardModel (class in pandemonium.networks)
G
Greedy (class in pandemonium.policies)
GVF (class in pandemonium.gvf)
gvf (Demon attribute)
H
hidden_state (ConvLSTM attribute)
HierarchicalPolicy (class in pandemonium.policies)
Horde (class in pandemonium.horde)
I
ICM (class in pandemonium.implementations)
Identity (class in pandemonium.networks)
implied_avf() (ControlDemon method)
interact() (Agent method)
InverseModel (class in pandemonium.networks)
is_empty (ER attribute)
is_full (ER attribute)
L
layer_init() (in module pandemonium.networks)
learn() (Agent method)
(Demon method)
(DQN method)
(Horde method)
(OnlineTD method)
(RewardPrediction method)
(ValueReplay method)
LinearDemon (class in pandemonium.demons)
LinearNet (class in pandemonium.networks)
lstm_state (ConvLSTM attribute)
M
memory_state (ConvLSTM attribute)
module
pandemonium.agent
pandemonium.continuations
pandemonium.cumulants
pandemonium.demons
pandemonium.experience
pandemonium.gvf
pandemonium.horde
pandemonium.implementations
pandemonium.networks
pandemonium.policies
pandemonium.traces
MultistepQLearning (class in pandemonium.implementations)
MultistepSARSA (class in pandemonium.implementations)
N
NatureCNN (class in pandemonium.networks)
O
OfflineTD (class in pandemonium.demons)
OfflineTDControl (class in pandemonium.demons)
OfflineTDPrediction (class in pandemonium.demons)
OnlineQLearning (class in pandemonium.implementations)
OnlineSARSA (class in pandemonium.implementations)
OnlineTD (class in pandemonium.demons)
OnlineTDControl (class in pandemonium.demons)
OnlineTDPrediction (class in pandemonium.demons)
P
pandemonium.agent
module
pandemonium.continuations
module
pandemonium.cumulants
module
pandemonium.demons
module
pandemonium.experience
module
pandemonium.gvf
module
pandemonium.horde
module
pandemonium.implementations
module
pandemonium.networks
module
pandemonium.policies
module
pandemonium.traces
module
ParametricDemon (class in pandemonium.demons)
PER (class in pandemonium.experience)
PixelChange (class in pandemonium.cumulants)
PixelControl (class in pandemonium.implementations)
Policy (class in pandemonium.policies)
predict() (Demon method)
predict_adv() (ControlDemon method)
predict_q() (ControlDemon method)
predict_target_adv() (ControlDemon method)
predict_target_q() (ControlDemon method)
PredictionDemon (class in pandemonium.demons)
Q
q_t() (DQN method)
(QLearning method)
(SARSA method)
(SARSE method)
(TDControl method)
q_tm1() (DQN method)
(TDControl method)
QLearning (class in pandemonium.demons)
R
randargmax() (in module pandemonium.policies)
Random (class in pandemonium.policies)
ReplayBuffer (class in pandemonium.experience)
ReplayBufferMixin (class in pandemonium.experience)
Reshape (class in pandemonium.networks)
Retrace (class in pandemonium.traces)
RewardPrediction (class in pandemonium.implementations)
S
sample() (ER method)
(PER method)
(SegmentedER method)
(SkewedER method)
SARSA (class in pandemonium.demons)
SARSE (class in pandemonium.demons)
SegmentedER (class in pandemonium.experience)
SigmoidContinuation (class in pandemonium.continuations)
SkewedER (class in pandemonium.experience)
SoftmaxPolicy (class in pandemonium.policies)
store() (ReplayBufferMixin method)
Surprise (class in pandemonium.cumulants)
sync_target() (TargetNetMixin method)
T
target() (OfflineTD method)
(OnlineTD method)
(OnlineTDPrediction method)
(RewardPrediction static method)
(TDControl method)
(TDPrediction method)
(TTD method)
target_policy() (GVF method)
TargetNetMixin (class in pandemonium.networks)
TDControl (class in pandemonium.demons)
TDn (class in pandemonium.demons)
TDPrediction (class in pandemonium.demons)
temperature (SoftmaxPolicy attribute)
TerminationCritic (class in pandemonium.continuations)
torch_argmax_mask() (in module pandemonium.policies)
Trajectory (class in pandemonium.experience)
Transition (class in pandemonium.experience)
TTD (class in pandemonium.demons)
U
update_priorities() (PER method)
V
v_t() (TDPrediction method)
ValueReplay (class in pandemonium.implementations)
VPG (class in pandemonium.policies)
Vtrace (class in pandemonium.traces)
Λ
λ (Demon attribute)
Μ
μ (Demon attribute)
Φ
φ (Demon attribute)