haoshengzou d599506dc9 fixed the bugs on Jan 14, which gives inferior or even no improvement. mistook group_ndims. policy will soon need refactoring.

2018-01-15 16:32:30 +08:00

..

.gitignore

fix memory growth and slowness caused by sess.run(tf.multinomial()), now ppo examples are working OK with slight memory growth (1M/min), which still needs research

2018-01-03 20:32:05 +08:00

dqn_example.py

finished all ppo examples. Training is remarkably slower than the version before Jan 13. More strangely, in the gym example there's almost no improvement... but this problem comes behind design. I'll first write actor-critic.

2018-01-15 00:03:06 +08:00

ppo_cartpole_alternative.py

finished all ppo examples. Training is remarkably slower than the version before Jan 13. More strangely, in the gym example there's almost no improvement... but this problem comes behind design. I'll first write actor-critic.

2018-01-15 00:03:06 +08:00

ppo_cartpole_gym.py

fixed the bugs on Jan 14, which gives inferior or even no improvement. mistook group_ndims. policy will soon need refactoring.

2018-01-15 16:32:30 +08:00

ppo_cartpole.py

finished all ppo examples. Training is remarkably slower than the version before Jan 13. More strangely, in the gym example there's almost no improvement... but this problem comes behind design. I'll first write actor-critic.

2018-01-15 00:03:06 +08:00