AI4Finance-Foundation / AI4Finance-Foundation/ElegantRL
Implementation bug in Prioritized Experience Replay
- Lenguaje dominante
- Python
- Estrellas
- 4.4k
- Forks
- 978
- Métricas de merge de PR
- Sin PR fusionados en 30 d
Descripción
File "/home/moderngangster/Codes/APC-Flight/ElegantRL/examples/../elegantrl/agents/AgentSAC.py", line 43, in update_net
obj_critic, state = self.get_obj_critic(buffer, self.batch_size)
File "/home/moderngangster/Codes/APC-Flight/ElegantRL/examples/../elegantrl/agents/AgentSAC.py", line 81, in get_obj_critic_per
states, actions, rewards, undones, next_ss, is_weights, is_indices = buffer.sample_for_per(batch_size)
File "/home/moderngangster/Codes/APC-Flight/ElegantRL/examples/../elegantrl/train/replay_buffer.py", line 134, in sample_for_per
_is_indices, _is_weights = sum_tree.important_sampling(batch_size, beg, end, self.per_beta)
File "/home/moderngangster/Codes/APC-Flight/ElegantRL/examples/../elegantrl/train/replay_buffer.py", line 267, in important_sampling
assert 0 <= i
Guía de contribución
No hay ninguna guía de contribución indexada para este repositorio
Evaluación
Este issue todavía no se ha evaluado.