reinforcement-learning

DQN with RNNs in TorchRL: Preventing Cross-Episode Leakage with Done Masks and SliceSampler

Oct. 31, 13:00

Why Your DQN Learns Nothing on Atari Pong: PyTorch Conv2d Channel Order Bug and the Fix

Oct. 25, 21:00

RLlib CTDE failures with PrioritizedEpisodeReplayBuffer on complex obs: use EpisodeReplayBuffer

Oct. 25, 17:00

ConditionalCategorical TypeError in pomegranate: use list-of-NumPy probs and set n_categories

Oct. 22, 09:00

1