We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 7d1f3a3 commit 09e3250Copy full SHA for 09e3250
d3rlpy/algos/qlearning/prdc.py
@@ -45,7 +45,7 @@ class PRDCConfig(LearnableConfig):
45
46
\lambda = \frac{\alpha}{\frac{1}{N} \sum_(s_i, a_i) |Q(s_i, a_i)|}
47
48
- and `d^\beta_\mathcal{D}(s,\pi(s))` is the DC loss, defined as
+ and :math:`d^\beta_\mathcal{D}(s,\pi(s))` is the DC loss, defined as
49
50
.. math::
51
docs/references/algos.rst
@@ -289,6 +289,18 @@ TD3+BC
289
:show-inheritance:
290
291
292
+PRDC
293
+----
294
+
295
+.. autoclass:: d3rlpy.algos.PRDCConfig
296
+ :members:
297
+ :show-inheritance:
298
299
+.. autoclass:: d3rlpy.algos.PRDC
300
301
302
303
304
ReBRAC
305
------
306
0 commit comments