Sven MikaandGitHub f7e4dae852 [RLlib] DQN and SAC Atari benchmark fixes. (#7962) ...

* Add Atari SAC-discrete (learning MsPacman in 40k ts up to 780 rewards).
* SAC loss function test case fix.

2020-04-17 08:49:15 +02:00

..

a3c

[RLlib] SAC Torch (incl. Atari learning) (#7984)

2020-04-15 13:25:16 +02:00

ars

[rllib] Rename sample_batch_size => rollout_fragment_length (#7503)

2020-03-14 12:05:04 -07:00

ddpg

[RLlib] DDPG PyTorch version. (#7953)

2020-04-16 10:20:01 +02:00

dqn

[RLlib] DDPG PyTorch version. (#7953)

2020-04-16 10:20:01 +02:00

es

[rllib] Rename sample_batch_size => rollout_fragment_length (#7503)

2020-03-14 12:05:04 -07:00

impala

[RLlib] Exploration API: Policy changes needed for forward pass noisifications. (#7798)

2020-04-01 00:43:21 -07:00

marwil

[RLlib] MARWIL torch. (#7836)

2020-04-06 16:38:50 -07:00

pg

[RLlib] SAC Torch (incl. Atari learning) (#7984)

2020-04-15 13:25:16 +02:00

ppo

[RLlib] SAC Torch (incl. Atari learning) (#7984)

2020-04-15 13:25:16 +02:00

qmix

[rllib] Add test case that we don't have a hard torch dependency (#7926)

2020-04-07 18:07:39 -07:00

sac

[RLlib] DQN and SAC Atari benchmark fixes. (#7962)

2020-04-17 08:49:15 +02:00

__init__.py

[rllib] Try moving RLlib to top level dir (#5324)

2019-08-05 23:25:49 -07:00

agent.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00

callbacks.py

[RLlib] Added DefaultCallbacks which replaces old callbacks dict interface (#6972)

2020-04-16 16:06:42 -07:00

mock.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00

registry.py

[rllib] Support multi-agent training in pipeline impls, add easy flag to enable (#7338)

2020-03-02 15:16:37 -08:00

trainer_template.py

[RLlib] SAC Torch (incl. Atari learning) (#7984)

2020-04-15 13:25:16 +02:00

trainer.py

[RLlib] Added DefaultCallbacks which replaces old callbacks dict interface (#6972)

2020-04-16 16:06:42 -07:00