
Learning performance
Solved after 9909 episodes. Best 100-episode average reward was 1483.40 ± 85.93. (DoomHealthGathering-v0 is considered "solved" when the agent obtains an average reward of at least 1000.0 over 100 consecutive episodes.)
Solved after 9909 episodes. Best 100-episode average reward was 1483.40 ± 85.93. (DoomHealthGathering-v0 is considered "solved" when the agent obtains an average reward of at least 1000.0 over 100 consecutive episodes.)