Artur Niederfahrenhorst
|
960032a15f
[RLlib][RLModules] RNNs and RLModules (#32723)
|
1 年之前 |
Sven Mika
|
e14c9b1da5
[RLlib] Remove `vtrace_drop_last_ts` option and add proper vf bootstrapping to IMPALA and APPO. (#36013)
|
1 年之前 |
Artur Niederfahrenhorst
|
5b5d83cef9
[RLlib] Fix rest of PPO RL Modules tests (#35672)
|
1 年之前 |
Sven Mika
|
adfdbbdfa2
[RLlib] APPO+new-stack (Atari benchmark) - Preparatory PR 03 - PyTorch. (#34779)
|
1 年之前 |
kourosh hakhamaneshi
|
70c4d5ce7c
[RLlib][RLModule] Fixed a bug where on the new RLModule API we could not rollout (#33331)
|
1 年之前 |
Artur Niederfahrenhorst
|
2269d380da
[RLlib] Revert "[RLlib] Fixed a bug where on the new RLModule API we could not rollout on GPU (#33309)" (#33330)
|
1 年之前 |
kourosh hakhamaneshi
|
f4b12f8a58
[RLlib] Fixed a bug where on the new RLModule API we could not rollout on GPU (#33309)
|
1 年之前 |
Artur Niederfahrenhorst
|
9f5dfbd7d0
[RLlib] Remove conversions to config dicts from AlgorithmConfig objects. (#33239)
|
1 年之前 |
Avnish Narayan
|
2a2777c838
[build_base][RLlib] PPO TF RL Module with Policy (#31637)
|
1 年之前 |
Sven Mika
|
8e680c483c
[RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369)
|
1 年之前 |
kourosh hakhamaneshi
|
185c8a5ba5
[RLlib] RLmodule integration POC with existing torch policies (#29868)
|
1 年之前 |
Peyton Murray
|
7f431d7053
Bump black (and therefore click) versions (#29574)
|
2 年之前 |
Eric Liang
|
4963dfaae0
[api] Add API stability annotations for all RLlib symbols and add to LINT (#25060)
|
2 年之前 |
Balaji Veeramani
|
7f1bacc7dc
[CI] Format Python code with Black (#21975)
|
2 年之前 |
Sven Mika
|
f82880eda1
Revert "Revert [RLlib] POC: Deprecate `build_policy` (policy template) for torch only; PPOTorchPolicy (#20061) (#20399)" (#20417)
|
2 年之前 |
Amog Kamsetty
|
90dc5460d4
Revert "[RLlib] POC: Deprecate `build_policy` (policy template) for torch only; PPOTorchPolicy (#20061)" (#20399)
|
2 年之前 |
Sven Mika
|
5b1c8e46e1
[RLlib] POC: Deprecate `build_policy` (policy template) for torch only; PPOTorchPolicy (#20061)
|
2 年之前 |
Sven Mika
|
9c73871da0
[RLlib; Docs overhaul] Docstring cleanup: Evaluation (#19783)
|
3 年之前 |
Sven Mika
|
e3e6ed7aaa
[RLlib] Issues 17844, 18034: Fix n-step > 1 bug. (#18358)
|
3 年之前 |
Sven Mika
|
e973b726c2
[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. (#15273)
|
3 年之前 |
Sven Mika
|
bb8a286cbc
[RLlib] Support native tf.keras.Model (milestone toward obsoleting ModelV2 class). (#14684)
|
3 年之前 |
Sven Mika
|
04bc0a9828
[RLlib] Remove all non-trajectory view API code. (#14860)
|
3 年之前 |
Sven Mika
|
69202c6a7d
[RLlib] Obsolete usage tracking dict via sample batch. (#13065)
|
3 年之前 |
Sven Mika
|
2e3655e8a9
[RLlib] Issue 9071 A3C w/ RNN not working due to VF assuming no RNN. (#13238)
|
3 年之前 |
Sven Mika
|
b2bcab711d
[RLlib] Attention Nets: tf (#12753)
|
3 年之前 |
Sven Mika
|
ce96b03b07
[RLlib] MB-MPO cleanup (comments, docstrings, type annotations). (#11033)
|
4 年之前 |
Sven Mika
|
47eb6613b5
[RLlib] Remove unnecessary copies in `compute_advantages`. (#10897)
|
4 年之前 |
Sven Mika
|
d14b501692
[RLlib] First attempt at cleaning up algo code in RLlib: PG. (#10115)
|
4 年之前 |
Sven Mika
|
b0b0463161
[RLlib] Trajectory View API (preparatory cleanup and enhancements). (#9678)
|
4 年之前 |
Eric Liang
|
1e0e1a45e6
[rllib] Add type annotations for evaluation/, env/ packages (#9003)
|
4 年之前 |