Index
Symbols
AO*
LAO*
Rmax
SARSA(λ)
CoMDP
ADD, see algebraic decision diagrams
DEC-MDP
NOMDP
POMDP
transient
DEC-POMDP
BDD, see binary decision diagrams
A
abalone
action
continuous
actor-critic
natural (NAC)
adaptive dynamics learning (ADL)
adaptive play
admissible heuristic
agent
playing
algebraic backward induction
algorithm
envelope
offline
online
Shapley’s algorithm
simulation-based
approximation
capacity
operator
power
theory
B
Bayesian networks
dynamic
Bellman
operator
optimality principle
Bellman equation
algebraic
for POMDPs
possibilistic
bias optimality
bias-variance trade-off
biodiversity
C
co-evolution
communication
controlled stochastic process
covering number
criterion
γ-discounted
adapted average
average
finite
total reward
D
decision diagrams
algebraic
binary
decision trees
depth-width trade-off
deviation matrix
discount factor
dyna
dyna-Q
focused
dynamic programming
approximate
asynchronous
exact methods
for DEC-POMDPs
possibilistic
E
E3
ED-Dec-MDP
efficient play
eligibility trace
empirical error
equilibrium
in dominating strategies
in mixed strategies
Nash equilibrium
Nash equilibrium in mixed strategies
error
generalization
learning
temporal difference
expected payoff
expected utility
generalized
qualitative binary possibilistic
qualitative optimistic
qualitative pessimistic
experience replay
exploration/exploitation trade-off
F
factored policy gradient (FPG)
feature
vector
fictitious play
finite difference method
focused reinforcement learning
function approximation ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access