Feature 111 add copy method to environment

.github/workflows/build.yml

@@ -20,7 +20,7 @@ jobs:
     - uses: actions/checkout@v4
     - name: Install dependencies
       run: |
-        sudo apt-get install -y g++ cmake libboost-all-dev libgtest-dev libeigen3-dev
+        sudo apt-get install -y g++ cmake libboost-all-dev libgtest-dev libeigen3-dev libblas-dev
     - name: Configure CMake
       # Configure CMake in a 'build' subdirectory. `CMAKE_BUILD_TYPE` is only required if you are using a single-configuration generator such as make.
       # See https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html?highlight=cmake_build_type

CMakeLists.txt

@@ -92,13 +92,13 @@ INCLUDE_DIRECTORIES(src/)
 
 FILE(GLOB SRCS src/rlenvs/*.cpp
                src/rlenvs/api_server/*.cpp
-               src/rlenvs/detail/*.cpp
+			   src/rlenvs/envs/*.cpp
                src/rlenvs/envs/gymnasium/*.cpp
                src/rlenvs/envs/gymnasium/toy_text/*.cpp
                src/rlenvs/envs/gymnasium/classic_control/*.cpp
                src/rlenvs/envs/gymnasium/classic_control/vector/*.cpp
                src/rlenvs/envs/gdrl/*.cpp
-               src/rlenvs/envs/gym_pybullet_drones/*.cpp
+               #src/rlenvs/envs/gym_pybullet_drones/*.cpp
                src/rlenvs/envs/grid_world/*.cpp
 			   src/rlenvs/envs/connect2/*.cpp
 			   src/rlenvs/dynamics/*.cpp

examples/CMakeLists.txt

@@ -23,7 +23,7 @@ LINK_DIRECTORIES(${CMAKE_INSTALL_PREFIX})
 ADD_SUBDIRECTORY(example_1)
 ADD_SUBDIRECTORY(example_2)
 ADD_SUBDIRECTORY(example_3)
-ADD_SUBDIRECTORY(example_4)
+#ADD_SUBDIRECTORY(example_4)
 ADD_SUBDIRECTORY(example_5)
 ADD_SUBDIRECTORY(example_6)
 ADD_SUBDIRECTORY(example_7)

examples/example_1/example_1.cpp

@@ -21,7 +21,7 @@ void test_frozen_lake(){
 
     // make the environment
     std::unordered_map<std::string, std::any> options;
-    options.insert({"is_slippery", true});
+    options.insert({"is_slippery", false});
     env.make("v1", options);
 
     std::cout<<"Is environment created? "<<env.is_created()<<std::endl;
@@ -40,7 +40,8 @@ void test_frozen_lake(){
     std::cout<<time_step<<std::endl;
 
     // take an action in the environment
-    auto new_time_step = env.step(rlenvscpp::envs::gymnasium::FrozenLakeActionsEnum::RIGHT);
+	// 2 = RIGHT
+    auto new_time_step = env.step(2);
 
     std::cout<<new_time_step<<std::endl;
 
@@ -58,9 +59,22 @@ void test_frozen_lake(){
         std::cout<<std::get<2>(item)<<std::endl;
         std::cout<<std::get<3>(item)<<std::endl;
     }
+
+	action = env.sample_action();
+	new_time_step = env.step(action);
 
+    std::cout<<new_time_step<<std::endl;
+
     // synchronize the environment
     env.sync(std::unordered_map<std::string, std::any>());
+
+	auto copy_env = env.make_copy(1);
+	copy_env.reset();
+
+	std::cout<<"Org env cidx: "<<env.cidx()<<std::endl;
+	std::cout<<"Copy env cidx: "<<copy_env.cidx()<<std::endl;
+
+	copy_env.close();
 
     // close the environment
     env.close();
@@ -81,7 +95,8 @@ void test_taxi(){
     std::cout<<"Is environment alive? "<<env.is_alive()<<std::endl;
     std::cout<<"Number of valid actions? "<<env.n_actions()<<std::endl;
     std::cout<<"Number of states? "<<env.n_states()<<std::endl;
-
+
+
     // reset the environment
     auto time_step = env.reset(42, std::unordered_map<std::string, std::any>());
 
@@ -93,7 +108,8 @@ void test_taxi(){
     std::cout<<time_step<<std::endl;
 
     // take an action in the environment
-    auto new_time_step = env.step(rlenvscpp::envs::gymnasium::TaxiActionsEnum::RIGHT);
+	// move RIGHT
+    auto new_time_step = env.step(2);
 
     std::cout<<new_time_step<<std::endl;
 
@@ -111,10 +127,21 @@ void test_taxi(){
         std::cout<<std::get<2>(item)<<std::endl;
         std::cout<<std::get<3>(item)<<std::endl;
     }
-
+
+
+	auto copy_env_1 = env.make_copy(1);
+	copy_env_1.reset();
+
+	auto copy_env_2 = env.make_copy(2);
+	copy_env_2.reset();
+	std::cout<<"Org env cidx: "<<env.cidx()<<std::endl;
+	std::cout<<"Copy env 1 cidx: "<<copy_env_1.cidx()<<std::endl;
+	std::cout<<"Copy env 2 cidx: "<<copy_env_2.cidx()<<std::endl;
+
     // close the environment
     env.close();
-
+	copy_env_2.close();
+	copy_env_1.close();
 }
 
 
@@ -131,14 +158,24 @@ void test_black_jack(){
     auto state = env.reset();
 
     std::cout<<"Environment step..."<<std::endl;
-    env.step(rlenvscpp::envs::gymnasium::BlackJackActionsEnum::HIT);
-    env.step(rlenvscpp::envs::gymnasium::BlackJackActionsEnum::STICK);
+
+	// 0 = HIT
+	// 1 = STICK
+    env.step(0);
+    env.step(1);
 
     // synchronize the environment
     env.sync(std::unordered_map<std::string, std::any>());
 
+    auto copy_env = env.make_copy(1);
+	copy_env.reset();
+
+	std::cout<<"Org env cidx: "<<env.cidx()<<std::endl;
+	std::cout<<"Copy env cidx: "<<copy_env.cidx()<<std::endl;
+
     // close the environment
     env.close();
+	copy_env.close();
 
 }
 
@@ -170,7 +207,8 @@ void test_cliff_world(){
     std::cout<<time_step<<std::endl;
 
     // take an action in the environment
-    auto new_time_step = env.step(rlenvscpp::envs::gymnasium::CliffWorldActionsEnum::UP);
+	// 0 = UP
+    auto new_time_step = env.step(0);
 
     std::cout<<new_time_step<<std::endl;
 
@@ -192,8 +230,15 @@ void test_cliff_world(){
     // synchronize the environment
     env.sync(std::unordered_map<std::string, std::any>());
 
+    auto copy_env = env.make_copy(1);
+	copy_env.reset();
+
+	std::cout<<"Org env cidx: "<<env.cidx()<<std::endl;
+	std::cout<<"Copy env cidx: "<<copy_env.cidx()<<std::endl;
+
     // close the environment
     env.close();
+	copy_env.close();
 
 }
 

examples/example_5/example_5.cpp

@@ -25,13 +25,14 @@ namespace example_5{
 		rlenvscpp::envs::grid_world::Gridworld<4> env;
 
         std::unordered_map<std::string, std::any> options;
-        options["mode"] = std::any(rlenvscpp::envs::grid_world::to_string(rlenvscpp::envs::grid_world::GridWorldInitType::STATIC));
+        options["mode"] = std::any(GridWorldInitType::STATIC);
 
         env.make("v0", options);
 
 		std::cout<<"Number of actions: "<<env.n_actions()<<std::endl;
 		std::cout<<"Number of states:  "<<env.n_states()<<std::endl;
-
+		std::cout<<"Version:  "<<env.version()<<std::endl;
+		std::cout<<"Name:  "<<env.env_name()<<std::endl;
 		env.close();
 	}
 
@@ -42,13 +43,14 @@ namespace example_5{
 		rlenvscpp::envs::grid_world::Gridworld<4> env;
 
         std::unordered_map<std::string, std::any> options;
-        options["mode"] = std::any(rlenvscpp::envs::grid_world::to_string(rlenvscpp::envs::grid_world::GridWorldInitType::RANDOM));
+        options["mode"] = std::any(GridWorldInitType::RANDOM);
 
         env.make("v0", options);
 
 		std::cout<<"Number of actions: "<<env.n_actions()<<std::endl;
 		std::cout<<"Number of states:  "<<env.n_states()<<std::endl;
-
+		std::cout<<"Version:  "<<env.version()<<std::endl;
+		std::cout<<"Name:  "<<env.env_name()<<std::endl;
 		env.close();
 	}
 

examples/example_6/example_6.cpp

@@ -28,7 +28,8 @@ int main(){
 	std::cout<<"Number of actions: "<<env.n_actions()<<std::endl;
 
 	// make the environment
-	env.make("v1");
+	std::unordered_map<std::string, std::any> options;
+	env.make("v1", options);
 
 	auto time_step = env.reset();