REVIEW 3 cited by
The In-Sample Softmax for Offline Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Reinforcement learning (RL) agents can leverage batches of previously collected data to extract a reasonable control policy. An emerging issue in this offline RL setting, however, is that the bootstrapping update underlying many of our methods suffers from insufficient action-coverage: standard max operator may select a maximal action that has not been seen in the dataset. Bootstrapping from these inaccurate values can lead to overestimation and even divergence. There are a growing number of methods that attempt to approximate an \emph{in-sample} max, that only uses actions well-covered by the dataset. We highlight a simple fact: it is more straightforward to approximate an in-sample \emph{softmax} using only actions in the dataset. We show that policy iteration based on the in-sample softmax converges, and that for decreasing temperatures it approaches the in-sample max. We derive an In-Sample Actor-Critic (AC), using this in-sample softmax, and show that it is consistently better or comparable to existing offline RL methods, and is also well-suited to fine-tuning.
Forward citations
Cited by 3 Pith papers
-
Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL
CSDG modifies the offline Bellman backup by scaling a smoothed convex-hull-neighborhood correction against an in-sample expectile target and reports strong D4RL aggregate performance.
-
Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning
Chained n-step endpoint coresets plus expectile Sarsa match million-transition DQN buffers at 10–50× less storage by keeping bootstrap targets anchored.
-
Are Expressive Models Truly Necessary for Offline RL?
A two-layer MLP with recursive skip-step sub-goal planning can reach state-of-the-art offline RL scores on long-horizon D4RL tasks, challenging the need for large expressive models.
Discussion (0). Continue with ORCID to comment.