When attempting to train a DDPG agent in a Pendulum-v0 environment, I ran into this error:
Traceback (most recent call last): File "/path/to/spinningup/spinup/utils/run_entrypoint.py", line 11, in <module> thunk() File "/path/to/spinningup/spinup/utils/run_utils.py", line 162, in thunk_plus thunk(**kwargs) File "/path/to/spinningup/spinup/algos/ddpg/ddpg.py", line 224, in ddpg replay_buffer.store(o, a, r, o2, d) File "/path/to/spinningup/spinup/algos/ddpg/ddpg.py", line 25, in store self.obs2_buf[self.ptr] = next_obs ValueError: could not broadcast input array from shape (3,1) into shape (3)
When attempting to train a DDPG agent in a Pendulum-v0 environment, I ran into this error:
Traceback (most recent call last): File "/path/to/spinningup/spinup/utils/run_entrypoint.py", line 11, in <module> thunk() File "/path/to/spinningup/spinup/utils/run_utils.py", line 162, in thunk_plus thunk(**kwargs) File "/path/to/spinningup/spinup/algos/ddpg/ddpg.py", line 224, in ddpg replay_buffer.store(o, a, r, o2, d) File "/path/to/spinningup/spinup/algos/ddpg/ddpg.py", line 25, in store self.obs2_buf[self.ptr] = next_obs ValueError: could not broadcast input array from shape (3,1) into shape (3)
The command I used was
python -m spinup.run ddpg --env Pendulum-v0 --exp_name ddpgtest
Python version is Python 3.6.7.