Open adityauser opened 4 years ago
Issue 1: At line: https://github.com/uber-research/deep-neuroevolution/blob/6ab22e190d3c0102a945dcce0c1d744eb610bdb9/es_distributed/ga.py#L230 The rollout function returns 3 objects, due to which we getting an error: ValueError: too many values to unpack (expected 2) It could be solved by replacing line 230 with: eval_rews, eval_length, _ = policy.rollout(env) Issue 2: At line: https://github.com/uber-research/deep-neuroevolution/blob/6ab22e190d3c0102a945dcce0c1d744eb610bdb9/es_distributed/ga.py#L143 It should be lengths_n2 = np.concatenate([r.lengths_n2 for r in curr_task_results]) very much similar to https://github.com/uber-research/deep-neuroevolution/blob/6ab22e190d3c0102a945dcce0c1d744eb610bdb9/es_distributed/es.py#L276 Otherwise lengths_n2.mean() andlengths_n2.sum() will have multiple dimension.
ValueError: too many values to unpack (expected 2)
eval_rews, eval_length, _ = policy.rollout(env)
lengths_n2 = np.concatenate([r.lengths_n2 for r in curr_task_results])
lengths_n2.mean()
lengths_n2.sum()
Issue 1: At line: https://github.com/uber-research/deep-neuroevolution/blob/6ab22e190d3c0102a945dcce0c1d744eb610bdb9/es_distributed/ga.py#L230 The rollout function returns 3 objects, due to which we getting an error:
ValueError: too many values to unpack (expected 2)It could be solved by replacing line 230 with:eval_rews, eval_length, _ = policy.rollout(env)Issue 2: At line: https://github.com/uber-research/deep-neuroevolution/blob/6ab22e190d3c0102a945dcce0c1d744eb610bdb9/es_distributed/ga.py#L143 It should belengths_n2 = np.concatenate([r.lengths_n2 for r in curr_task_results])very much similar to https://github.com/uber-research/deep-neuroevolution/blob/6ab22e190d3c0102a945dcce0c1d744eb610bdb9/es_distributed/es.py#L276 Otherwiselengths_n2.mean()andlengths_n2.sum()will have multiple dimension.