Sven Mika
|
9c73871da0
[RLlib; Docs overhaul] Docstring cleanup: Evaluation (#19783)
|
3 年之前 |
Sven Mika
|
902e854af2
[RLlib; Docs overhaul] Docstring cleanup: Environments. (#19784)
|
3 年之前 |
Antoine Galataud
|
edb338ff7c
[RLlib] Check `training_enabled` on PolicyServer (#19007)
|
3 年之前 |
Sven Mika
|
61a1274619
[RLlib] No Preprocessors (part 2). (#18468)
|
3 年之前 |
Sven Mika
|
fd13bac9b3
[RLlib] Add `worker` arg (optional) to `policy_mapping_fn`. (#18184)
|
3 年之前 |
Sven Mika
|
8a066474d4
[RLlib] No Preprocessors; preparatory PR #1 (#18367)
|
3 年之前 |
gjoliver
|
336e79956a
[RLlib] Make MultiAgentEnv inherit gym.Env to avoid direct class type manipulation (#18156)
|
3 年之前 |
Sven Mika
|
2357bbc0c8
[RLlib] Issue 18231: Better (earlier) env validation and error message improvement. (#18249)
|
3 年之前 |
Joseph Suarez
|
8136d2912b
[RLlib] Add `policies` arg to callback: `on_episode_step` (already exists in all other episode-related callbacks) (#18119)
|
3 年之前 |
Sven Mika
|
494ddd98c1
[RLlib] Replace "seq_lens" w/ SampleBatch.SEQ_LENS. (#17928)
|
3 年之前 |
Kai Fricke
|
bf3eaa9264
[RLlib] Dreamer fixes and reinstate Dreamer test. (#17821)
|
3 年之前 |
Sven Mika
|
f18213712f
[RLlib] Redo: "fix self play example scripts" PR (17566) (#17895)
|
3 年之前 |
Sven Mika
|
29f20cccb6
[RLlib] Issue 17706: AttributeError: 'numpy.ndarray' object has no attribute 'items'" on certain turn-based MultiAgentEnvs with Dict obs space. (#17735)
|
3 年之前 |
Amog Kamsetty
|
77f28f1c30
Revert "[RLlib] Fix `Trainer.add_policy` for num_workers>0 (self play example scripts). (#17566)" (#17709)
|
3 年之前 |
Sven Mika
|
3b447265d8
[RLlib] Fix `Trainer.add_policy` for num_workers>0 (self play example scripts). (#17566)
|
3 年之前 |
Sven Mika
|
18d173b172
[RLlib] Implement policy_maps (multi-agent case) in RolloutWorkers as LRU caches. (#17031)
|
3 年之前 |
Sven Mika
|
53206dd440
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)
|
3 年之前 |
Eric Liang
|
1c709cbeb3
Fix typing (#16668)
|
3 年之前 |
Sven Mika
|
be6db06485
[RLlib] Re-do: Trainer: Support add and delete Policies. (#16569)
|
3 年之前 |
Sven Mika
|
79a9d6d517
[RLlib] Issues 16287 and 16200: RLlib not rendering custom multi-agent Envs. (#16428)
|
3 年之前 |
Amog Kamsetty
|
bd3cbfc56a
Revert "[RLlib] Allow policies to be added/deleted on the fly. (#16359)" (#16543)
|
3 年之前 |
Sven Mika
|
e78ec370a9
[RLlib] Allow policies to be added/deleted on the fly. (#16359)
|
3 年之前 |
Amog Kamsetty
|
ebc44c3d76
[CI] Upgrade flake8 to 3.9.1 (#15527)
|
3 年之前 |
Sven Mika
|
1c9701e9cb
[RLlib] Discussion 1513: `on_episode_step()` callback called after very first reset (should not). (#15218)
|
3 年之前 |
Sven Mika
|
04bc0a9828
[RLlib] Remove all non-trajectory view API code. (#14860)
|
3 年之前 |
Sven Mika
|
3e7899d251
[RLlib] Issue 14653: Empty env steps cause key error in SimpleListCollector. (#14765)
|
3 年之前 |
Sven Mika
|
f859ebb99f
[RLlib] Fix env rendering and recording options (for non-local mode; >0 workers; +evaluation-workers). (#14796)
|
3 年之前 |
Chris Bamford
|
cd89f0dc55
[RLLib] Episode media logging support (#14767)
|
3 年之前 |
Sven Mika
|
929946271d
[RLlib] Issue #14022: Trajectory View API fails in MA-env where a new agent terminates right away (done=True right after initial obs). (#14031)
|
3 年之前 |
Sven Mika
|
d001af3e59
[RLlib] Allow `rllib rollout` to run distributed via evaluation workers. (#13718)
|
3 年之前 |