edit documentation

Author: SidhartK

docs/make.jl

@@ -12,21 +12,22 @@ makedocs(
         ##############################################
         "Basics" => [
             "index.md",
-            # "install.md",
+            "mdp.md",
             # "get_started.md",
             # "concepts.md"
            ],
-        "Usage" => [
-            "mdp.md",
-            # "pomdp.md",
-            # "simplegame.md",
-            # "mg.md",
-            # "pomg.md",
-            # "decpomdp.md"
-           ],
+        # "Usage" => [
+        #     "mdp.md",
+        #     # "pomdp.md",
+        #     # "simplegame.md",
+        #     # "mg.md",
+        #     # "pomg.md",
+        #     # "decpomdp.md"
+        #    ],
 
 
         "MDP Models" => [
+            # "mdp.md",
             "hexworld.md",
             "2048.md",
             "cart_pole.md",
@@ -36,26 +37,31 @@ makedocs(
            ],
 
         "POMDP Models" => [
+            "pomdp.md",
             "crying_baby.md",
             "machine_replacement.md",
             "catch.md"
            ],
 
         "Simple Games" => [
+            "simplegame.md",
             "prisoners_dilemma.md",
             "rock_paper_scissors.md",
             "travelers.md"
            ],
 
         "POMG Models" => [
+            "pomg.md",
             "multicaregiver.md",
            ],
 
         "Markov Game" => [
+            "mg.md",
             "predator_prey.md",
            ],
 
         "Dec-POMDP" => [
+            "decpomdp.md",
             "collab_predator_prey.md",
            ],
         # "Concepts" => [

docs/src/decpomdp.md

@@ -0,0 +1,14 @@
+# DecPOMDP Usage
+
+## Decentralized POMDP
+The DecPOMDP struct gives the following objects:
+ - `γ`: discount factor
+ - `ℐ`: agents
+ - `𝒮`: state space
+ - `𝒜`: joint action space
+ - `𝒪`: joint observation space
+ - `T`: transition function
+ - `O`: joint observation function
+ - `R`: joint reward function
+
+ The agents `ℐ` are the players of the game. The joint action space `𝒜` is the set of all possible ordered pairs of actions amongst all of the agents. The joint observation space `𝒪` is the set of all possible joint observations. The transition function takes in a state `s` in `𝒮`, a joint action `a` and a new state `s'`and returns the transition probability of going from `s` to `s'` by taking action `a`. The joint observation function takes in a state, `s`, a joint action, `a`, and a joint observation `o` in `𝒪` and returns a probability of observing `o` by taking action `a` from state `s`. The joint reward function `R` takes a state and a joint action in `𝒜` and returns a reward value.

docs/src/index.md

@@ -5,13 +5,6 @@
 
 ![Problem Summary](figures/problemsum.svg)
 
-### Usage
-
-```@contents
-Pages = [ "mdp.md" ]
-```
-
-
 ### MDP Models
 
 ```@contents
@@ -21,29 +14,29 @@ Pages = [ "hexworld.md", "2048.md", "cart_pole.md", "mountain_car.md", "simple_l
 ### POMDP Models
 
 ```@contents
-Pages = [ "crying_baby.md", "machine_replacement.md", "catch.md" ]
+Pages = [ "pomdp.md", "crying_baby.md", "machine_replacement.md", "catch.md" ]
 ```
 
 ### Simple Games
 
 ```@contents
-Pages = [ "prisoners_dilemma.md", "rock_paper_scissors.md", "travelers.md" ]
+Pages = [ "simplegame.md", "prisoners_dilemma.md", "rock_paper_scissors.md", "travelers.md" ]
 ```
 
 ### POMG Models
 
 ```@contents
-Pages = [ "multicaregiver.md" ]
+Pages = [ "pomg.md", "multicaregiver.md" ]
 ```
 
 ### Markov Games
 
 ```@contents
-Pages = [ "predator_prey.md" ]
+Pages = [ "mg.md", "predator_prey.md" ]
 ```
 
 ### Dec-POMDP
 
 ```@contents
-Pages = [ "collab_predator_prey.md" ]
+Pages = [ "decpomdp.md", "collab_predator_prey.md" ]
 ```

docs/src/mg.md

@@ -0,0 +1,12 @@
+# MG Usage
+
+## Markov Game
+The MG struct gives the following objects:
+ - `γ`: discount factor
+ - `ℐ`: agents
+ - `𝒮`: state space
+ - `𝒜`: joint action space
+ - `T`: transition function
+ - `R`: joint reward function
+
+ The agents `ℐ` are the players of the game. The joint action space `𝒜` is the set of all possible ordered pairs of actions amongst all of the agents. The transition function takes in a state `s` in `𝒮`, a joint action `a` and a new state `s'` and returns the transition probability of going from `s` to `s'` by taking action `a`. The joint reward function `R` takes a state and a joint action in `𝒜` and returns a reward value.

docs/src/pomg.md

@@ -0,0 +1,14 @@
+# POMG Usage
+
+## Partially Observable Markov Game
+The POMG struct gives the following objects:
+ - `γ`: discount factor
+ - `ℐ`: agents
+ - `𝒮`: state space
+ - `𝒜`: joint action space
+ - `𝒪`: joint observation space
+ - `T`: transition function
+ - `O`: joint observation function
+ - `R`: joint reward function
+
+ The agents `ℐ` are the players of the game. The joint action space `𝒜` is the set of all possible ordered pairs of actions amongst all of the agents. The joint observation space `𝒪` is the set of all possible joint observations. The transition function takes in a state `s` in `𝒮`, a joint action `a` and a new state `s'`and returns the transition probability of going from `s` to `s'` by taking action `a`. The joint observation function takes in a state, `s`, a joint action, `a`, and a joint observation `o` in `𝒪` and returns a probability of observing `o` by taking action `a` from state `s`. The joint reward function `R` takes a state and a joint action in `𝒜` and returns a reward value.

docs/src/simplegame.md

@@ -0,0 +1,10 @@
+# SimpleGame Usage
+
+## Simple Game
+The SimpleGame struct gives the following objects:
+ - `γ`: discount factor
+ - `ℐ`: agents
+ - `𝒜`: joint action space
+ - `R`: joint reward function
+
+The agents `ℐ` in a simple game are the players of the game. The joint action space `𝒜` is the set of all possible ordered pairs of actions amongst all of the agents. The joint reward function `R` takes a joint action in `𝒜` and returns a reward value.