Deep Reinforcement Learning with pytorch and visdom


  • Sample testings of trained agents (DQN on Breakout, A3C on Pong, DoubleDQN on CartPole, continuous A3C on InvertedPendulum(MuJoCo)):
  • Sample on-line plotting while training an A3C agent on Pong (with 16 learner processes): a3c_pong_plot

  • Sample loggings while training a DQN agent on CartPole (we use WARNING as the logging level currently to get rid of the INFO printouts from visdom):