.. |
a2c
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
a3c
|
1c636e7c30
[RLlib] DreamerV3: Learner API classes for tf-keras, loss functions, additional update method. (#35385)
|
1 年之前 |
alpha_star
|
adfdbbdfa2
[RLlib] APPO+new-stack (Atari benchmark) - Preparatory PR 03 - PyTorch. (#34779)
|
1 年之前 |
alpha_zero
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
apex_ddpg
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
apex_dqn
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
appo
|
960032a15f
[RLlib][RLModules] RNNs and RLModules (#32723)
|
1 年之前 |
ars
|
8427de2776
[RLlib] Fix ARS release test (#35608)
|
1 年之前 |
bandits
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
bc
|
94ed6f99a3
[RLlib] BC RLModule. (#39542)
|
1 年之前 |
cql
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
crr
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
ddpg
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
ddppo
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
dqn
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
dreamer
|
b52a81b3de
[RLlib] Preparation for gymnasium/gym0.26 upgrade: Deprecate `horizon` and `soft_horizon` settings. (#30583)
|
1 年之前 |
dreamerv3
|
b0045799e3
[RLlib] DreamerV3: Make 200M (XL model) work; mixed float16 option (#38461)
|
1 年之前 |
dt
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
es
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
impala
|
78b58a959a
[RLlib] Learner API: Policies using RLModules (for sampler only) do not need loss/stats/mixins. (#34445)
|
1 年之前 |
leela_chess_zero
|
f80badcdb0
[RLlib] Remove leela chess from release tests (#32325)
|
1 年之前 |
maddpg
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
maml
|
b52a81b3de
[RLlib] Preparation for gymnasium/gym0.26 upgrade: Deprecate `horizon` and `soft_horizon` settings. (#30583)
|
1 年之前 |
marwil
|
8d2dc9a399
[RLlib] Change default framework from tf to torch (#33604)
|
1 年之前 |
mbmpo
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
pg
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
ppo
|
8d80377445
[RLlib] Fixed 'rollout_fragment_length' in pong-example by setting it to 'auto'. (#39552)
|
1 年之前 |
qmix
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
r2d2
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
sac
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
simple_q
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
slateq
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
td3
|
2dbd5fbeac
[RLlib] Add throughput per-second metrics (env/agent steps trained and -sampled) to Algorithm. (#34526)
|
1 年之前 |
__init__.py
|
7243d56185
[RLlib] python-based training from cli (to make tuned examples more pythonic) (#29459)
|
2 年之前 |
cleanup_experiment.py
|
7f1bacc7dc
[CI] Format Python code with Black (#21975)
|
2 年之前 |
compact-regression-test.yaml
|
8e680c483c
[RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369)
|
1 年之前 |
create_plots.py
|
baa053496a
[RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414)
|
4 年之前 |