Merge branch '47-update-to-new-gym-api' into gym_upgrade

fancy_gym/examples/examples_dmc.py

@@ -26,10 +26,10 @@ def example_dmc(env_id="dmc:fish-swim", seed=1, iterations=1000, render=True):
         ac = env.action_space.sample()
         if render:
             env.render(mode="human")
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         rewards += reward
 
-        if done:
+        if terminated or truncated:
             print(env_id, rewards)
             rewards = 0
             obs = env.reset()
@@ -102,10 +102,10 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
     # number of samples/full trajectories (multiple environment steps)
     for i in range(iterations):
         ac = env.action_space.sample()
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         rewards += reward
 
-        if done:
+        if terminated or truncated:
             print(base_env_id, rewards)
             rewards = 0
             obs = env.reset()

fancy_gym/examples/examples_general.py

@@ -1,6 +1,6 @@
 from collections import defaultdict
 
-import gym
+import gymnasium as gym
 import numpy as np
 
 import fancy_gym
@@ -29,13 +29,13 @@ def example_general(env_id="Pendulum-v1", seed=1, iterations=1000, render=True):
 
     # number of environment steps
     for i in range(iterations):
-        obs, reward, done, info = env.step(env.action_space.sample())
+        obs, reward, terminated, truncated, info = env.step(env.action_space.sample())
         rewards += reward
 
         if render:
             env.render()
 
-        if done:
+        if terminated or truncated:
             print(rewards)
             rewards = 0
             obs = env.reset()
@@ -69,12 +69,15 @@ def example_async(env_id="HoleReacher-v0", n_cpu=4, seed=int('533D', 16), n_samp
     # this would generate more samples than requested if n_samples % num_envs != 0
     repeat = int(np.ceil(n_samples / env.num_envs))
     for i in range(repeat):
-        obs, reward, done, info = env.step(env.action_space.sample())
+        obs, reward, terminated, truncated, info = env.step(env.action_space.sample())
         buffer['obs'].append(obs)
         buffer['reward'].append(reward)
-        buffer['done'].append(done)
+        buffer['terminated'].append(terminated)
+        buffer['truncated'].append(truncated)
         buffer['info'].append(info)
         rewards += reward
+
+        done = terminated or truncated
         if np.any(done):
             print(f"Reward at iteration {i}: {rewards[done]}")
             rewards[done] = 0

fancy_gym/examples/examples_metaworld.py

@@ -29,9 +29,9 @@ def example_dmc(env_id="fish-swim", seed=1, iterations=1000, render=True):
             # THIS NEEDS TO BE SET TO FALSE FOR NOW, BECAUSE THE INTERFACE FOR RENDERING IS DIFFERENT TO BASIC GYM
             # TODO: Remove this, when Metaworld fixes its interface.
             env.render(False)
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         rewards += reward
-        if done:
+        if terminated or truncated:
             print(env_id, rewards)
             rewards = 0
             obs = env.reset()
@@ -103,10 +103,10 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
     # number of samples/full trajectories (multiple environment steps)
     for i in range(iterations):
         ac = env.action_space.sample()
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         rewards += reward
 
-        if done:
+        if terminated or truncated:
             print(base_env_id, rewards)
             rewards = 0
             obs = env.reset()
@@ -131,4 +131,3 @@ if __name__ == '__main__':
     #
     # # Custom MetaWorld task
     example_custom_dmc_and_mp(seed=10, iterations=1, render=render)
-

fancy_gym/examples/examples_movement_primitives.py

@@ -41,11 +41,11 @@ def example_mp(env_name="HoleReacherProMP-v0", seed=1, iterations=1, render=True
         # This executes a full trajectory and gives back the context (obs) of the last step in the trajectory, or the
         # full observation space of the last step, if replanning/sub-trajectory learning is used. The 'reward' is equal
         # to the return of a trajectory. Default is the sum over the step-wise rewards.
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         # Aggregated returns
         returns += reward
 
-        if done:
+        if terminated or truncated:
             print(reward)
             obs = env.reset()
 
@@ -79,10 +79,10 @@ def example_custom_mp(env_name="Reacher5dProMP-v0", seed=1, iterations=1, render
     # number of samples/full trajectories (multiple environment steps)
     for i in range(iterations):
         ac = env.action_space.sample()
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         returns += reward
 
-        if done:
+        if terminated or truncated:
             print(i, reward)
             obs = env.reset()
 
@@ -145,10 +145,10 @@ def example_fully_custom_mp(seed=1, iterations=1, render=True):
     # number of samples/full trajectories (multiple environment steps)
     for i in range(iterations):
         ac = env.action_space.sample()
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         rewards += reward
 
-        if done:
+        if terminated or truncated:
             print(rewards)
             rewards = 0
             obs = env.reset()

fancy_gym/examples/examples_open_ai.py

@@ -24,10 +24,10 @@ def example_mp(env_name, seed=1, render=True):
         else:
             env.render()
         ac = env.action_space.sample()
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
         returns += reward
 
-        if done:
+        if terminated or truncated:
             print(returns)
             obs = env.reset()
 

fancy_gym/examples/pd_control_gain_tuning.py

@@ -34,7 +34,7 @@ fig.show()
 for t, pos_vel in enumerate(zip(pos, vel)):
     actions = env.tracking_controller.get_action(pos_vel[0], pos_vel[1], env.current_vel, env.current_pos)
     actions = np.clip(actions, env.env.action_space.low, env.env.action_space.high)
-    _, _, _, _ = env.env.step(actions)
+    env.env.step(actions)
     if t % 15 == 0:
         img.set_data(env.env.render(mode="rgb_array"))
         fig.canvas.draw()