Yu Zheng

Results 2 comments of Yu Zheng

Thanks. My question is actually that can PPOAgent support multiple discrete actions? I found no tutorials about this topic.

> The specs don't match PolicyStep(action=., state=(), info={'dist_params': {}, 'value_prediction': .}) vs. PolicyStep(action=., state=(), info=DictWrapper({'dist_params': DictWrapper({'logits': .}), 'value_prediction': .})) > > Make sure the policy builds the correct info data....