Created
December 1, 2017 18:02
-
-
Save WilliamJou/8d28f48744b7231c4a816715e8dd8ec6 to your computer and use it in GitHub Desktop.
Error using SARSOP
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
importall POMDPs | |
using POMDPToolbox | |
using SARSOP | |
using BasicPOMCP | |
using D3Trees | |
using ParticleFilters | |
const DISH = 1 | |
const HAND = 2 | |
const TEMPS = 0:10:30 | |
const TINDEX = Dict{Int, Int}(t=>i for (i,t) in enumerate(TEMPS)) | |
struct FState | |
task::Int | |
time::Int | |
prev_temp::Int | |
end | |
struct FPOMDP <: POMDP{FState, Int, Int} | |
p_change::Float64 | |
max_time::Int | |
end | |
p = FPOMDP(0.5, 10) | |
const DTEMP = Dict{Int, Int}(DISH=>30, HAND=>20) | |
isterminal(p::FPOMDP, s::FState) = s.time > p.max_time | |
states(p::FPOMDP) = vec(collect(FState(task, time, pt) for task in [DISH, HAND], time in 0:p.max_time, pt in TEMPS)) | |
n_states(p::FPOMDP) = length(TEMPS)*(p.max_time+1)*2 | |
const SINDEX = Dict{FState, Int}(s=>i for (i,s) in enumerate(states(p))) | |
state_index(p::FPOMDP, s::FState) = SINDEX[s] | |
actions(p::FPOMDP) = TEMPS | |
n_actions(p::FPOMDP) = length(TEMPS) | |
action_index(p::FPOMDP, a::Int) = TINDEX[a] | |
observations(p::FPOMDP) = TEMPS | |
n_observations(p::FPOMDP) = length(TEMPS) | |
obs_index(p::FPOMDP, o::Int) = TINDEX[o] | |
function transition(p::FPOMDP, s::FState, a::Int) | |
SparseCat([FState(s.task, s.time+1, a)], [1.0]) | |
end | |
function observation(p::FPOMDP, a::Int, sp::FState) | |
if sp.time > 2 && a != DTEMP[sp.task] | |
return SparseCat([DTEMP[sp.task], 0], [0.5, 0.5]) | |
else | |
return SparseCat([0], [1.0]) | |
end | |
end | |
function reward(p::FPOMDP, s::FState, a::Int) | |
if a == DTEMP[s.task] | |
return 10.0 | |
else | |
return -10.0 | |
end | |
end | |
initial_state_distribution(p::FPOMDP) = SparseCat([FState(t, 0, 0) for t in [DISH, HAND]], [0.5, 0.5]) | |
# policy = RandomPolicy(p) | |
solver = SARSOPSolver() | |
#solver = POMCPSolver(c=100) | |
policy = solve(solver, p) | |
for (b, s, a, r, o) in stepthrough(p, policy, "bsaro") | |
frac_hand = length(filter(s->s.task==HAND, particles(b)))/n_particles(b) | |
@show frac_hand | |
@show s | |
@show a | |
@show r | |
@show o | |
end | |
inchrome(D3Tree(policy)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment