hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-06 10:31:39 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions
ray/rllib/tuned_examples/regression_tests
History
Sven Mika d0fab84e4d
[RLlib] DDPG PyTorch version. (#7953) 
The DDPG/TD3 algorithms currently do not have a PyTorch implementation. This PR adds PyTorch support for DDPG/TD3 to RLlib.
This PR:
- Depends on the re-factor PR for DDPG (Functional Algorithm API).
- Adds learning regression tests for the PyTorch version of DDPG and a DDPG (torch)
- Updates the documentation to reflect that DDPG and TD3 now support PyTorch.

* Learning Pendulum-v0 on torch version (same config as tf). Wall time a little slower (~20% than tf).
* Fix GPU target model problem.
2020-04-16 10:20:01 +02:00
..
cartpole-a2c-microbatch.yaml [rllib] Add microbatch optimizer with A2C example (#6161) 2019-11-14 12:14:00 -08:00
cartpole-a2c-torch.yaml [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
cartpole-a3c.yaml [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
cartpole-appo-vtrace.yaml [rllib] Rename sample_batch_size => rollout_fragment_length (#7503) 2020-03-14 12:05:04 -07:00
cartpole-appo.yaml [rllib] Rename sample_batch_size => rollout_fragment_length (#7503) 2020-03-14 12:05:04 -07:00
cartpole-ars.yaml [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
cartpole-ddppo.yaml [rllib] Add Decentralized DDPPO trainer and documentation (#7088) 2020-02-10 15:28:27 -08:00
cartpole-dqn-tf-param-noise.yaml [RLlib] DQN torch version. (#7597) 2020-04-06 11:56:16 -07:00
cartpole-dqn-tf.yaml [RLlib] DQN torch version. (#7597) 2020-04-06 11:56:16 -07:00
cartpole-dqn-torch-param-noise.yaml [RLlib] DQN torch version. (#7597) 2020-04-06 11:56:16 -07:00
cartpole-dqn-torch.yaml [RLlib] DQN torch version. (#7597) 2020-04-06 11:56:16 -07:00
cartpole-es.yaml [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
cartpole-pg-tf.yaml [RLlib] Add PG torch regression test (#6828) 2020-01-18 15:57:12 -08:00
cartpole-pg-torch.yaml [RLlib] Add PG torch regression test (#6828) 2020-01-18 15:57:12 -08:00
cartpole-ppo-tf.yaml [RLlib] PPO(torch) on CartPole not tuned well enough for consistent learning (#7556) 2020-03-11 20:31:27 -07:00
cartpole-ppo-torch.yaml [RLlib] PPO(torch) on CartPole not tuned well enough for consistent learning (#7556) 2020-03-11 20:31:27 -07:00
cartpole-sac-tf.yaml [RLlib] SAC Torch (incl. Atari learning) (#7984) 2020-04-15 13:25:16 +02:00
cartpole-sac-torch.yaml [RLlib] SAC Torch (incl. Atari learning) (#7984) 2020-04-15 13:25:16 +02:00
cartpole-simpleq-tf.yaml [RLlib] DQN torch version. (#7597) 2020-04-06 11:56:16 -07:00
cartpole-simpleq-torch.yaml [RLlib] DQN torch version. (#7597) 2020-04-06 11:56:16 -07:00
pendulum-appo-vtrace.yaml [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
pendulum-ddpg-tf.yaml [RLlib] DDPG PyTorch version. (#7953) 2020-04-16 10:20:01 +02:00
pendulum-ddpg-torch.yaml [RLlib] DDPG PyTorch version. (#7953) 2020-04-16 10:20:01 +02:00
pendulum-ppo.yaml [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
pendulum-sac-tf.yaml [RLlib] SAC Torch (incl. Atari learning) (#7984) 2020-04-15 13:25:16 +02:00
pendulum-sac-torch.yaml [RLlib] SAC Torch (incl. Atari learning) (#7984) 2020-04-15 13:25:16 +02:00
pendulum-td3.yaml [RLlib] DDPG refactor and Exploration API action noise classes. (#7314) 2020-03-01 11:53:35 -08:00