Merge pull request #18 from yangyou95/master

Add convert_s function

Author: zsunberg

src/LaserTag.jl

@@ -19,29 +19,23 @@ export
     LTState,
     CMeas,
     DMeas,
-    LaserTagVis,
-
-    MoveTowards,
+    LaserTagVis, MoveTowards,
     MoveTowardsSampled,
     OptimalMLSolver,
     OptimalML,
     BestExpectedSolver,
-    BestExpected,
-
-    DESPOTEmu,
-
-    gen_lasertag,
+    BestExpected, DESPOTEmu, gen_lasertag,
     cpp_emu_lasertag,
     tikz_pic,
     n_clear_cells
 
 
-const Coord = SVector{2, Int}
-const CMeas = MVector{8, Float64}
-const DMeas = MVector{8, Int}
+const Coord = SVector{2,Int}
+const CMeas = MVector{8,Float64}
+const DMeas = MVector{8,Int}
 
-const C_SAME_LOC = fill!(MVector{8, Float64}(undef), -1.0)
-const D_SAME_LOC = fill!(MVector{8, Int64}(undef), -1)
+const C_SAME_LOC = fill!(MVector{8,Float64}(undef), -1.0)
+const D_SAME_LOC = fill!(MVector{8,Int64}(undef), -1)
 
 @auto_hash_equals struct LTState # XXX auto_hash_equals isn't correct for terminal
     robot::Coord
@@ -71,16 +65,16 @@ obs_type(om::ObsModel) = obs_type(typeof(om))
 
 include("distance_cache.jl")
 
-@with_kw struct LaserTagPOMDP{M<:ObsModel, O<:Union{CMeas, DMeas}} <: POMDP{LTState, Int, O}
-    tag_reward::Float64         = 10.0
-    step_cost::Float64          = 1.0
-    discount::Float64           = 0.95
-    floor::Floor                = Floor(7, 11)
-    obstacles::Set{Coord}       = Set{Coord}()
-    robot_init::Union{Coord, Nothing} = nothing
-    diag_actions::Bool          = false
-    dcache::LTDistanceCache     = LTDistanceCache(floor, obstacles)
-    obs_model::M                = DESPOTEmu(floor, 2.5)
+@with_kw struct LaserTagPOMDP{M<:ObsModel,O<:Union{CMeas,DMeas}} <: POMDP{LTState,Int,O}
+    tag_reward::Float64 = 10.0
+    step_cost::Float64 = 1.0
+    discount::Float64 = 0.95
+    floor::Floor = Floor(7, 11)
+    obstacles::Set{Coord} = Set{Coord}()
+    robot_init::Union{Coord,Nothing} = nothing
+    diag_actions::Bool = false
+    dcache::LTDistanceCache = LTDistanceCache(floor, obstacles)
+    obs_model::M = DESPOTEmu(floor, 2.5)
 end
 
 ltfloor(m::LaserTagPOMDP) = m.floor
@@ -142,6 +136,16 @@ function POMDPs.reward(p::LaserTagPOMDP, s::LTState, a::Int, sp::LTState)
     end
 end
 
+function POMDPs.convert_s(T::Type{<:AbstractArray}, s::LTState, p::LaserTagPOMDP)
+    vals = SVector{5, Float64}(s.robot..., s.opponent..., s.terminal)
+    return convert(T, vals)
+end
+
+function POMDPs.convert_s(T::Type{LTState}, v::AbstractArray, p::LaserTagPOMDP)
+    return LTState(Coord(v[1], v[2]), Coord(v[3], v[4]), v[5])
+end
+
+
 POMDPs.isterminal(p::LaserTagPOMDP, s::LTState) = s.terminal
 POMDPs.discount(p::LaserTagPOMDP) = p.discount
 

test/runtests.jl

@@ -6,6 +6,7 @@ using POMDPTools
 using ParticleFilters
 using POMDPs
 using StableRNGs
+using StaticArrays
 
 @time p = gen_lasertag()
 
@@ -59,6 +60,17 @@ for dir in 1:8
     @test total == N
 end
 
+@testset "convert_s" begin
+    s_test = rand(rng, initialstate(p))
+    
+    for VT in [Vector{Float64}, SVector]
+        v_s_test = convert_s(VT, s_test, p)
+        @test v_s_test isa VT
+        s_back = convert_s(LTState, v_s_test, p)
+        @test s_back == s_test
+    end
+end
+
 pol = RandomPolicy(p, rng=StableRNG(1))
 
 sim = HistoryRecorder(max_steps=10, rng=StableRNG(2))