keras-rl - v0.4.2

• Fix Tensorboard support
• Improve documentation

- Python
Published by RaphaelMeudec about 8 years ago

keras-rl - v0.4.1

• Add support for current version of Keras and Gym

- Python
Published by RaphaelMeudec over 8 years ago

keras-rl - v0.4.0

• Removes legacy code and now requires Keras >= 2.0.7 (https://github.com/matthiasplappert/keras-rl/pull/157)
• Adds two new policies (https://github.com/matthiasplappert/keras-rl/pull/156, https://github.com/matthiasplappert/keras-rl/pull/122)
• Fixes a few problems with replay memory sampling being incorrect for certain edge cases (https://github.com/matthiasplappert/keras-rl/pull/138)
• Fixes a problem with dropout in actor model for DDPG (https://github.com/matthiasplappert/keras-rl/pull/150)

- Python
Published by matthiasplappert over 8 years ago

keras-rl - v0.3.1

• Require Keras < 2.0.7 due to non-trivial and breaking API change in optimizer code

- Python
Published by matthiasplappert almost 9 years ago

keras-rl -

• Full compatibility with the recently released Keras 2
• New SarsaAgent implementation
• New train_policy on DQNAgent and SarsaAgent to allow for different policies at training and test time
• Minor clean-ups

- Python
Published by matthiasplappert over 9 years ago

keras-rl -

• Fix version mix-up on release, otherwise identical to version v0.2.1

- Python
Published by matthiasplappert over 9 years ago

keras-rl -

• Add Dueling DQN
• Add support for TensorFlow 1.0
• Fix problem with default policy if multiple DQN agents are used simultaneously

- Python
Published by matthiasplappert over 9 years ago

keras-rl - v0.2.0rc1

- Python
Published by matthiasplappert over 9 years ago