Kaiwen Bian

Comparing different decoder architecture's effect on the training process. Particularly looking at MLP decoder and LSTM decoder with customized BPTT length (unroll-length), all experiments here are generated with BPTT-20.

MARL trainig rendering & curves report for various RL agents v.s. bots and RL agents v.s. RL agents, demonstrating the main theme of AlphaTank repo: "not all the actions that the agent make is sensable, but it works!" It represents something that the agent have learned, something that is not human intelligence.