MX-2000

MAKE_FNS = {
    'breakout':      lambda: lazy_import('pufferlib.ocean.breakout.breakout', 'Breakout'),
    'pong':          lambda: lazy_import('pufferlib.ocean.pong.pong', 'Pong'),
    'enduro':        lambda: lazy_import('pufferlib.ocean.enduro.enduro', 'Enduro'),
    'moba':          lambda: lazy_import('pufferlib.ocean.moba.moba', 'Moba'),
    'nmmo3':         lambda: lazy_import('pufferlib.ocean.nmmo3.nmmo3', 'NMMO3'),
    'snake':         lambda: lazy_import('pufferlib.ocean.snake.snake', 'Snake'),
    'squared':       lambda: lazy_import('pufferlib.ocean.squared.squared', 'Squared'),
    'pysquared':     lambda: lazy_import('pufferlib.ocean.squared.pysquared', 'PySquared'),
    'connect4':      lambda: lazy_import('pufferlib.ocean.connect4.connect4', 'Connect4'),

MX-2000

#define EMPTY 0
#define NORMAL_FOOD 1
#define INTERACTIVE_FOOD 2
// Anything above Wall should be obstacles
#define WALL 3
#define AGENTS 4

#define LOG_BUFFER_SIZE 8192

#define SET_BIT(arr, i) (arr[(i) / 8] |= (1 << ((i) % 8)))

MX-2000

void step_agent(CCpr *env, int i) {

  int action = env->actions[i];

  int dr = 0;
  int dc = 0;

  switch (action) {
  case 0:
    dr = -1;

MX-2000

void c_step(CCpr *env) {

  memset(env->rewards, 0, env->num_agents * sizeof(float));
  memset(env->interactive_food_agent_count, 0,
         (env->width * env->height + 7) / 8);

  for (int i = 0; i < env->num_agents; i++) {
    step_agent(env, i);
  }

MX-2000

void c_reset(CCpr *env) {
  env->tick = 0;

  for (int r = 0; r < env->height; r++) {
    for (int c = 0; c < env->width; c++) {
      int adr = grid_index(env, r, c);
      env->grid[adr] = EMPTY;
    }
  }

MX-2000

void compute_observations(CCpr *env) {
  for (int i = 0; i < env->num_agents; i++) {
    Agent *agent = &env->agents[i];
    int obs_offset = i * env->obs_size;
    int r_offset = agent->r - env->vision;
    int c_offset = agent->c - env->vision;
    for (int r = 0; r < 2 * env->vision + 1; r++) {
      for (int c = 0; c < 2 * env->vision + 1; c++) {
        int grid_idx = (r_offset + r) * env->width + c_offset + c;
        int obs_idx = obs_offset + r * env->vision_window + c;

MX-2000

void spawn_foods(CCpr *env) {
  // After each step, check existing foods and spawns new food in the
  // neighborhood Iterates over food_list for efficiency instead of the entire
  // grid.
  FoodList *foods = env->foods;
  int original_size = foods->size;
  for (int i = 0; i < original_size; i++) {
    int idx = foods->indexes[i];
    int offset = idx - env->width - 1; // Food spawn in 1 radius
    int r = offset / env->width;

MX-2000

typedef struct FoodList FoodList;
struct FoodList {
  int *indexes; // Grid flattened index positions
  int size;
};

MX-2000

typedef struct CCpr CCpr;
struct CCpr {
  int width;
  int height;
  int num_agents;

  int vision;
  int vision_window;
  int obs_size;

MX-2000

typedef struct Agent Agent;
struct Agent {
  int r;
  int c;
  int id;
};