ValueError: too many values to unpack (expected 4)

[ppangTae]

---

ValueError Traceback (most recent call last)
/home/parksangtae/RL-Adventure-master/1.dqn.ipynb Cell 19 line 1
[11] epsilon = epsilon_by_frame(frame_idx)
[12] action = model.act(state, epsilon)
---> [14] next_state, reward, done, _ = env.step(action)
[15] replay_buffer.push(state, action, reward, next_state, done)
[17] state = next_state

ValueError: too many values to unpack (expected 4)

could you tell me why this error is happen?

[ciel0906]

The same. Have you resolved this issue?

[wxxiong]

Have a try. "next_state, reward, done, _, _ = env.step(action)" for five values to unpack

[daisukisatone]

Have a try. "next_state, reward, done, _, _ = env.step(action)" for five values to unpack

I tried. But new errors may arise, "ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2,) + inhomogeneous part."

[wxxiong]

chage all the code "state = env.reset()" to "state, _ = env.reset()"