Regarding our IMPALA implementation: It currently also only supports discrete actions. However, our SAC algo is extremely strong. It learned (continuous) Pendulum-v0 within only a few dozen episodes, so you could try…
Regarding our IMPALA implementation: It currently also only supports discrete actions. However, our SAC algo is extremely strong. It learned (continuous) Pendulum-v0 within only a few dozen episodes, so you could try…