def reset(self):
obs = self.env.reset()
sim = self.unwrapped.sim
# Get indexes of qvel for movement debuff
self.agent_qvel_idxs = [
qvel_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
]
# Get indexes of qpos of agents
self.agent_qpos_idxs = np.array([
qpos_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
# Get indexes of obstacles pos
self.obstacles_id = [
sim.model.body_name2id("B1"),
sim.model.body_name2id("B2"),
sim.model.body_name2id("B3"),
sim.model.body_name2id("B4"),
sim.model.body_name2id("B5"),
sim.model.body_name2id("B6"),
sim.model.body_name2id("B7"),
sim.model.body_name2id("B8"),
sim.model.body_name2id("B9")
]
return self.observation(obs)
def modify_sim_step(self, env, sim):
# Cache qpos, qvel idxs
self.ramp_qpos_idxs = np.array([qpos_idxs_from_joint_prefix(sim, f'ramp{i}')
for i in range(self.n_ramps)])
self.ramp_qvel_idxs = np.array([qvel_idxs_from_joint_prefix(sim, f'ramp{i}')
for i in range(self.n_ramps)])
self.ramp_geom_idxs = np.array([sim.model.geom_name2id(f'ramp{i}:ramp')
for i in range(self.n_ramps)])
def reset(self):
obs = self.env.reset()
sim = self.unwrapped.sim
# Get agent qpos idx
self.agent_qpos_idxs = np.array([
qpos_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
return self.observation(obs)
def modify_sim_step(self, env, sim):
# Cache qpos, qvel idxs
self.box_geom_idxs = np.array([sim.model.geom_name2id(f'moveable_box{i}')
for i in range(self.curr_n_boxes)])
self.box_qpos_idxs = np.array([qpos_idxs_from_joint_prefix(sim, f'moveable_box{i}:')
for i in range(self.curr_n_boxes)])
self.box_qvel_idxs = np.array([qvel_idxs_from_joint_prefix(sim, f'moveable_box{i}:')
for i in range(self.curr_n_boxes)])
if self.mark_box_corners:
self.box_corner_idxs = np.array([sim.model.site_name2id(f'moveable_box{i}_corner{j}')
for i in range(self.curr_n_boxes)
for j in range(4)])
def modify_sim_step(self, env, sim):
if self.make_static:
self.s_cylinder_geom_idxs = np.array([sim.model.geom_name2id(f'static_cylinder{i}')
for i in range(self.n_objects)])
else:
self.m_cylinder_geom_idxs = np.array([sim.model.geom_name2id(f'moveable_cylinder{i}')
for i in range(self.n_objects)])
qpos_idxs = [qpos_idxs_from_joint_prefix(sim, f'moveable_cylinder{i}')
for i in range(self.n_objects)]
qvel_idxs = [qvel_idxs_from_joint_prefix(sim, f'moveable_cylinder{i}')
for i in range(self.n_objects)]
self.m_cylinder_qpos_idxs = np.array(qpos_idxs)
self.m_cylinder_qvel_idxs = np.array(qvel_idxs)
def modify_sim_step(self, env, sim):
# Cache qpos, qvel idxs
self.agent_qpos_idxs = np.array([
qpos_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
self.agent_qvel_idxs = np.array([
qvel_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
env.metadata['agent_geom_idxs'] = [
sim.model.geom_name2id(f'agent{i}:agent')
for i in range(self.n_agents)
]
def reset(self):
obs = self.env.reset()
sim = self.unwrapped.sim
# Get new position
self.destinations = np.array(
[[np.random.uniform(0.0, 8080),
np.random.uniform(0.0, 4480)],
[np.random.uniform(0.0, 8080),
np.random.uniform(0.0, 4480)]])
# Get agent xy qpos
self.agent_qpos_idxs = np.array([
qpos_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
return self.observation(obs)
def modify_sim_step(self, env, sim):
# Cache qpos, qvel idxs
self.agent_qpos_idxs = np.array([
qpos_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
self.agent_qvel_idxs = np.array([
qvel_idxs_from_joint_prefix(sim, f'agent{i}')
for i in range(self.n_agents)
])
env.metadata['agent_geom_idxs'] = [
sim.model.site_name2id(f'agent{i}:agent')
for i in range(self.n_agents)
]
# Randomize starting orientation of agents
for i in range(self.n_agents):
#rqpos = qpos_idxs_from_joint_prefix(sim, f'agent{i}:rz')
rqpos = self.agent_qpos_idxs[i, -1]
sim.data.qpos[rqpos] = np.random.uniform(low=0, high=6.28319)
