Title: Bayesian Sparse Sampling for On-line Reward Optimization
1Bayesian Sparse Sampling for On-line Reward
Optimization
Presented in the Value of Information Seminar at
NIPS 2005
Based on previous paper from ICML 2005, written
by Dale Schuurmans et all
2Background Perspective
- Be Bayesian about reinforcement learning
- Ideal representation of uncertainty for
action selection - Computational barriers
Why are Bayesian approaches not prevalent in RL?
3Exploration vs. Exploitation
- Bayes decision theory
- Value of information measured by ultimate return
in reward - Choose actions to max expected value
- Exploration/exploitation tradeoff implicitly
handled as side effect
4Bayesian Approach
conceptually clean but computationally disasterous
versus
conceptually disasterous but computationally clean
5Bayesian Approach
conceptually clean but computationally disasterous
versus
conceptually disasterous but computationally clean
6Overview
- Efficient lookahead search for Bayesian RL
- Sparser sparse sampling
- Controllable computational cost
- Higher quality action selection than current
methods
Greedy Epsilon - greedy Boltzmann Thompson
Sampling Bayes optimal Interval estimation
Myopic value of perfect info. Standard sparse
sampling Péret Garcia
(Luce 1959) (Thompson 1933) (Hee 1978) (Lai
1987, Kaelbling 1994) (Dearden, Friedman, Andre
1999) (Kearns, Mansour, Ng 2001) (Péret Garcia
2004)
7Sequential Decision Making
Requires model P(r,ss,a)
How to make an optimal decision?
s
V(s)
Planning
a
a
MAX
s,a
s,a
Q(s,a)
Q(s,a)
r
r
r
r
expectation
expectation
s
s
s
s
V(s)
V(s)
V(s)
V(s)
a
a
a
a
a
a
a
a
MAX
MAX
MAX
MAX
s,a
s,a
s,a
s,a
s,a
s,a
s,a
s,a
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
r
r
r
r
r
r
r
r
r
r
r
r
r
r
r
r
E
E
E
E
E
E
E
E
s
s
s
s
s
s
s
s
s
s
s
s
s
s
s
s
This is finite horizon, finite action, finite
reward case
General case Fixed point equations
8Reinforcement Learning
Do not have model P(r,ss,a)
s
V(s)
a
a
MAX
s,a
s,a
Q(s,a)
Q(s,a)
r
r
r
r
expectation
expectation
s
s
s
s
V(s)
V(s)
V(s)
V(s)
a
a
a
a
a
a
a
a
MAX
MAX
MAX
MAX
s,a
s,a
s,a
s,a
s,a
s,a
s,a
s,a
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
r
r
r
r
r
r
r
r
r
r
r
r
r
r
r
r
E
E
E
E
E
E
E
E
s
s
s
s
s
s
s
s
s
s
s
s
s
s
s
s
9Reinforcement Learning
Do not have model P(r,ss,a)
s
V(s)
a
a
MAX
s,a
s,a
Q(s,a)
Q(s,a)
r
r
r
r
expectation
expectation
s
s
s
s
V(s)
V(s)
V(s)
V(s)
a
a
a
a
a
a
a
a
MAX
MAX
MAX
MAX
s,a
s,a
s,a
s,a
s,a
s,a
s,a
s,a
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
Q(s,a)
r
r
r
r
r
r
r
r
r
r
r
r
r
r
r
r
E
E
E
E
E
E
E
E
s
s
s
s
s
s
s
s
s
s
s
s
s
s
s
s
10Bayesian Reinforcement Learning
Belief state bP(?)
Prior P(?) on model P(rs sa, ?)
Meta-level MDP
meta-level state
s b
decision a
a
Choose action to maximize long term reward
actions
s b a
outcome r, s, b
Meta-level Model P(r,sbs b,a)
rewards
r
s b
decision a
a
actions
s b a
outcome r, s, b
Meta-level Model P(r,sbs b,a)
rewards
r
s b
Have a model for meta-level transitions! - based
on posterior update and expectations over
base-level MDPs
11Bayesian RL Decision Making
How to make an optimal decision?
V(s b)
Bayes optimal action selection
Solve planning problem in meta-level MDP
a
a
MAX
Q(s b, a)
Q(s b, a)
- Optimal Q,V values
r
r
r
r
E
E
V(s b)
V(s b)
V(s b)
V(s b)
Problem meta-level MDP much larger than
base-level MDP
Impractical
12Bayesian RL Decision Making
Current approximation strategies
Consider current belief state b
s b
s
a
a
a
a
MAX
MAX
Draw a base-level MDP
s b, a
s b, a
s, a
s, a
E
E
r
r
r
r
r
r
r
r
E
E
s b
s b
s b
s b
s
s
s
s
? Exploration is based on uncertainty
Greedy approach current b ? mean base-level MDP
model ? point estimate for Q, V
? choose greedy action
Thompson approach current b ? sample a
base-level MDP model ? point estimate
for Q, V (Choose action proportional to
probability it is max Q)
But doesnt consider uncertainty
But still myopic
13Their Approach
- Try to better approximate Bayes optimal action
selection by performing lookahead - Adapt sparse sampling (Kearns, Mansour ,Ng)
- Make some practical improvements
14Sparse Sampling
(Kearns, Mansour, Ng 2001)
15Bayesian Sparse SamplingObservation 1
- Action value estimates are not equally important
- Need better Q value estimates for some actions
but not all - Preferentially expand tree under actions that
might be optimal
MAX
Biased tree growth Use Thompson sampling to
select actions to expand
16Bayesian Sparse SamplingObservation 2
- Correct leaf value estimates to same depth
MAX
Use mean MDP Q-value multiplied by remaining
depth
t1
E
t2
E
t3
effective horizon N3
17Bayesian Sparse SamplingTree growing procedure
1. Sample prior for a model 2. Solve action
values 3. Select the optimal action
- Descend sparse tree from root
- Thompson sample actions
- Sample outcome
- Until new node added
- Repeat until tree size limit reached
s,b
s,b,a
Execute action Observe reward
sb
Control computation by controlling tree size
18Simple experiments
- 5 Bernoulli bandits
- Beta priors
- Sampled model from prior
- Run action selection strategies
- Repeat 3000 times
- Average accumulated reward per step
19(No Transcript)
20(No Transcript)
21That's it