hsp
hsp copied to clipboard
Hierarchical Self-Play
I am looking for a simple reinforce/a2c example to work with Mazebase environments. It seems like Mazebase repo is no longer compatible with this repo? I get this error from...
Process ThreadedWorker-4: Traceback (most recent call last): File "/home/ubuntu16/anaconda3/envs/rllab3/lib/python3.5/multiprocessing/process.py", line 249, in _bootstrap self.run() File "/home/ubuntu16/hsp-master/hsp/multi_threading.py", line 19, in run batch, stat = self.trainer.run_batch() File "/home/ubuntu16/hsp-master/hsp/trainer.py", line 277, in run_batch...