We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| philippe-eecs/idql | canonical | 2 of 2 |
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| exp_w_clip | Ran | philippe-eecs/idql/jaxrl5/agents/ddpm_iql/ddpm_iql_learner.py pointer only (licence: NONE) · get_code("eb87f275461ed086") |
| expectile_loss | Ran | this paper's copy was not recorded; identical code first harvested from ZhengYinan-AIR/FISOR pointer only · get_code("ad221b0896e1bcd0") |
| quantile_loss | Ran | philippe-eecs/idql/jaxrl5/agents/ddpm_iql/ddpm_iql_learner.py pointer only (licence: NONE) · get_code("bcaf26b4b210fed0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions through a modified Bellman backup. However, it is unclear which policy actually attains the values represented by this implicitly trained Q-function. In this paper, we reinterpret IQL as an actor-critic method by generalizing the critic objective and connecting it to a behavior-regularized implicit actor. This generalization shows how the induced actor balances reward maximization and divergence from the behavior policy, with the specific loss choice determining the nature of this tradeoff. Notably, this actor can exhibit complex and multimodal characteristics, suggesting issues with the conditional Gaussian actor fit with advantage weighted regression (AWR) used in prior methods. Instead, we propose using samples from a diffusion parameterized behavior policy and weights computed from the critic to then importance sampled our intended policy. We introduce Implicit Diffusion Q-learning (IDQL), combining our general IQL critic with the policy extraction method. IDQL maintains the ease of implementation of IQL while outperforming prior offline RL methods and demonstrating robustness to hyperparameters. Code is available at https://github.com/philippe-eecs/IDQL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.10573")
get_code_for_paper("2304.10573")
have("2304.10573")
Connect an agent — have() is free.