Sven Mika
|
eea6b40a3e
[RLlib] Minor cleanups in `Trainer`; better tf/tf2 info messages about possible tracing speedups. (#20109)
|
2 年之前 |
Sven Mika
|
a931076f59
[RLlib] Tf2 + eager-tracing same speed as framework=tf; Add more test coverage for tf2+tracing. (#19981)
|
3 年之前 |
Sven Mika
|
2d24ef0d32
[RLlib] Add all simple learning tests as `framework=tf2`. (#19273)
|
3 年之前 |
Sven Mika
|
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829)
|
3 年之前 |
Sven Mika
|
bab9c0f670
[RLlib; Docs overhaul] Redo: Docstring cleanup: Trainer, trainer_template, Callbacks."" (#19830)
|
3 年之前 |
Sven Mika
|
9c73871da0
[RLlib; Docs overhaul] Docstring cleanup: Evaluation (#19783)
|
3 年之前 |
Sven Mika
|
4a82d3ea6c
Revert "[RLlib; Docs overhaul] Docstring cleanup: Trainer, trainer_template, Callbacks. (#19758)" (#19806)
|
3 年之前 |
Sven Mika
|
80eeb13175
[RLlib; Docs overhaul] Docstring cleanup: Trainer, trainer_template, Callbacks. (#19758)
|
3 年之前 |
gjoliver
|
99a0088233
[RLlib] Unify the way we create local replay buffer for all agents (#19627)
|
3 年之前 |
Sven Mika
|
fd438d5630
[RLlib] Issue 18104: Cannot set remote_worker_envs=True for non local-mode and MultiAgentEnv. (#19133)
|
3 年之前 |
Sven Mika
|
828f5d26b7
[RLlib] Custom view requirements (e.g. for prev-n-obs) work with `compute_single_action` and `compute_actions_from_input_dict`. (#18921)
|
3 年之前 |
Sven Mika
|
61a1274619
[RLlib] No Preprocessors (part 2). (#18468)
|
3 年之前 |
Sven Mika
|
698b4eeed3
[RLlib] POC: Separate losses for APPO/IMPALA. Enable TFPolicy to handle multiple optimizers/losses (like TorchPolicy). (#18669)
|
3 年之前 |
Sven Mika
|
3f89f35e52
[RLlib] Better error messages and hints; + failure-mode tests; (#18466)
|
3 年之前 |
Sven Mika
|
8a066474d4
[RLlib] No Preprocessors; preparatory PR #1 (#18367)
|
3 年之前 |
Sven Mika
|
1520c3d147
[RLlib] Deepcopy env_ctx for vectorized sub-envs AND add eval-worker-option to `Trainer.add_policy()` (#18428)
|
3 年之前 |
Sven Mika
|
56f142cac1
[RLlib] Add support for evaluation_num_episodes=auto (run eval for as long as the parallel train step takes). (#18380)
|
3 年之前 |
Sven Mika
|
ba58f5edb1
[RLlib] Strictly run `evaluation_num_episodes` episodes each evaluation run (no matter the other eval config settings). (#18335)
|
3 年之前 |
Sven Mika
|
a772c775cd
[RLlib] Set random seed (if provided) to Trainer process as well. (#18307)
|
3 年之前 |
Sven Mika
|
82465f9342
[RLlib] Better PolicyServer example (w/ or w/o tune) and add printing out actual listen port address in log-level=INFO. (#18254)
|
3 年之前 |
Sven Mika
|
599e589481
[RLlib] Move existing fake multi-GPU learning tests into separate buildkite job. (#18065)
|
3 年之前 |
Sven Mika
|
4888d7c9af
[RLlib] Replay buffers: Add config option to store contents in checkpoints. (#17999)
|
3 年之前 |
Sven Mika
|
9883505e84
[RLlib] Add [LSTM=True + multi-GPU]-tests to nightly RLlib testing suite (for all algos supporting RNNs, except R2D2, RNNSAC, and DDPPO). (#18017)
|
3 年之前 |
Sven Mika
|
8248ba531b
[RLlib] Redo #17410: Example script: Remote worker envs with inference done on main node. (#17960)
|
3 年之前 |
Alex Wu
|
318ba6fae0
Revert "[RLlib] Add example script for how to have n remote (parallel) envs with inference happening on "main" (possibly GPU) node. (#17410)" (#17951)
|
3 年之前 |
Sven Mika
|
8fc16b9a18
[RLlib] Add example script for how to have n remote (parallel) envs with inference happening on "main" (possibly GPU) node. (#17410)
|
3 年之前 |
Sven Mika
|
f18213712f
[RLlib] Redo: "fix self play example scripts" PR (17566) (#17895)
|
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
|
5107d16ae5
[RLlib] Add @Deprecated decorator to simplify/unify deprecation of classes, methods, functions. (#17530)
|
3 年之前 |