Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix and unit test for issue #1079 #1081

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Fix and unit test for issue #1079 #1081

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
43a13a4
Fix and unit test for issue "Wrong style for state report for TicTacT…
hespanha Sep 3, 2024
b8572cc
Adapt TicTacToe fix
jeremiahpslewis Sep 3, 2024
e0b4d82
Refactor TicTacToe state / multiplayer handling
jeremiahpslewis Sep 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 9 additions & 10 deletions src/ReinforcementLearningEnvironments/src/environments/examples/TicTacToeEnv.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,20 +70,19 @@ end

RLBase.players(::TicTacToeEnv) = (Player(:Cross), Player(:Nought))

RLBase.state(env::TicTacToeEnv, ::Observation, ::DefaultPlayer) = state(env, Observation{Int}(), Player(:Any))
RLBase.state(env::TicTacToeEnv, ::Observation{BitArray{3}}, player) = env.board
RLBase.state(env::TicTacToeEnv, ::RLBase.AbstractStateStyle) = state(env::TicTacToeEnv, Observation{Int}(), Player(1))
RLBase.state(env::TicTacToeEnv, ::Observation{Int}, player::Player) =
RLBase.state(env::TicTacToeEnv, o::Observation, ::RLBase.AbstractPlayer) = state(env, o)
RLBase.state(env::TicTacToeEnv, ::RLBase.AbstractStateStyle) = state(env::TicTacToeEnv, Observation{Int}())
RLBase.state(env::TicTacToeEnv, ::Observation{BitArray{3}}) = env.board
RLBase.state(env::TicTacToeEnv, ::Observation{Int}) =
get_tic_tac_toe_state_info()[env].index

RLBase.state_space(env::TicTacToeEnv, ::Observation{BitArray{3}}, player::Player) = ArrayProductDomain(fill(false:true, 3, 3, 3))
RLBase.state_space(env::TicTacToeEnv, ::Observation{Int}, player::Player) =
RLBase.state_space(env::TicTacToeEnv, o::Observation, ::RLBase.AbstractPlayer) = state_space(env, o)
RLBase.state_space(::TicTacToeEnv, ::Observation{BitArray{3}}) = ArrayProductDomain(fill(false:true, 3, 3, 3))
RLBase.state_space(::TicTacToeEnv, ::Observation{Int}) =
Base.OneTo(length(get_tic_tac_toe_state_info()))
RLBase.state_space(env::TicTacToeEnv, ::Observation{String}, player::Player) = fullspace(String)
RLBase.state_space(::TicTacToeEnv, ::Observation{String}) = fullspace(String)

RLBase.state(env::TicTacToeEnv, ::Observation{String}) = state(env::TicTacToeEnv, Observation{String}(), Player(1))

function RLBase.state(env::TicTacToeEnv, ::Observation{String}, player::Player)
function RLBase.state(env::TicTacToeEnv, ::Observation{String})
buff = IOBuffer()
for i in 1:3
for j in 1:3
Expand Down
9 changes: 5 additions & 4 deletions src/ReinforcementLearningEnvironments/test/environments/examples/tic_tac_toe.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,15 @@
using ReinforcementLearningEnvironments, ReinforcementLearningBase, ReinforcementLearningCore

trajectory_1 = Trajectory(
CircularArraySARTSTraces(; capacity = 1),
CircularArraySARTSTraces(; capacity=1),
BatchSampler(1),
InsertSampleRatioController(n_inserted = -1),
InsertSampleRatioController(n_inserted=-1),
)

trajectory_2 = Trajectory(
CircularArraySARTSTraces(; capacity = 1),
CircularArraySARTSTraces(; capacity=1),
BatchSampler(1),
InsertSampleRatioController(n_inserted = -1),
InsertSampleRatioController(n_inserted=-1),
)

multiagent_policy = MultiAgentPolicy(PlayerTuple(
Expand All @@ -30,6 +30,7 @@
@test length(state_space(env, Observation{Int}())) == 5478

@test RLBase.state(env, Observation{BitArray{3}}(), Player(:Cross)) == env.board
@test RLBase.state(env, Observation{BitArray{3}}()) == env.board
@test RLBase.state_space(env, Observation{BitArray{3}}(), Player(:Cross)) isa ArrayProductDomain
@test RLBase.state_space(env, Observation{String}(), Player(:Cross)) isa DomainSets.FullSpace{String}
@test RLBase.state(env, Observation{String}(), Player(:Cross)) isa String
Expand Down
Loading