matthiasplappert · December 4, 2025 15:51 · KOHHHHHA · Dec 17, 2022 · dbalmhsnalnwr-ui · Dec 4, 2025
diff --git a/example.py b/example.py
 import numpy as np
 import gym


 env = gym.make('FetchReach-v0')
 obs = env.reset()
 done = False

 def policy(observation, desired_goal):
    # Here you would implement your smarter policy. In this case,
    # we just sample random actions.
    return env.action_space.sample()

 while not done:
    action = policy(obs['observation'], obs['desired_goal'])
    obs, reward, done, info = env.step(action)

    # If we want, we can substitute a goal here and re-compute
    # the reward. For instance, we can just pretend that the desired
    # goal was what we achieved all along.
    substitute_goal = obs['achieved_goal'].copy()
    substitute_reward = env.compute_reward(
        obs['achieved_goal'], substitute_goal, info)
    print('reward is {}, substitute_reward is {}'.format(
        reward, substitute_reward))
	import numpy as np
	import gym


	env = gym.make('FetchReach-v0')
	obs = env.reset()
	done = False

	def policy(observation, desired_goal):
	# Here you would implement your smarter policy. In this case,
	# we just sample random actions.
	return env.action_space.sample()

	while not done:
	action = policy(obs['observation'], obs['desired_goal'])
	obs, reward, done, info = env.step(action)

	# If we want, we can substitute a goal here and re-compute
	# the reward. For instance, we can just pretend that the desired
	# goal was what we achieved all along.
	substitute_goal = obs['achieved_goal'].copy()
	substitute_reward = env.compute_reward(
	obs['achieved_goal'], substitute_goal, info)
	print('reward is {}, substitute_reward is {}'.format(
	reward, substitute_reward))
No results found