Keras Rl Versions Save

Deep Reinforcement Learning for Keras.

v0.4.2

6 years ago

Fix Tensorboard support
Improve documentation

V0.4.1

6 years ago

Add support for current version of Keras and Gym

v0.4.0

6 years ago

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)

v0.3.1

6 years ago

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

v0.3.0

7 years ago

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

v0.2.2

7 years ago

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

v0.2.1

7 years ago

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

v0.2.0rc1

7 years ago