v2.4.1

What's Changed

• new harder hypergrid tasks by @josephdviviano in #495
• general cleanup @josephdviviano in #496, #479
  #491, #504, #505
• Add getting started notebook with HyperGrid FM example by @josephdviviano in #497
• Add seven-segment display graph GFlowNet tutorial by @josephdviviano and @younik in #498
• Add optional custom log_rewards to all GFlowNet losses by @josephdviviano in #503
• Add Chip Design environment by @younik in #407
• Fix pyproject.toml: move Pyright report* settings out of pytest config by @Copilot in
• Increase test coverage by @josephdviviano in #506

Full Changelog: v2.4.0...v2.4.1

v2.4.0

What's Changed

Here's a summary of the torchgfn changes heading into v2.4.0:

Major Features

• Relative Trajectory Balance (#457, @josephdviviano) — new loss objective added to the library.
• Conditional GFlowNets refactor (#431, @hyeok9855) — reworked how conditioning works end-to-end, including renaming conditioning → conditions (#430) and placing conditions within States (#445).
• torch.compile utility & benchmark harness (#443, #460, #481, @josephdviviano) — deterministic-mode toggle (#444), debug-mode fast paths for states/actions (#449), and a benchmark suite for tracking performance.
• Local replay buffer accumulation (#446, @chirayuharyan).
• Optimized loss computation (#451, @josephdviviano) — restructured the GFlowNet loss path for efficiency.

Minor Features & Fixes

• Detailed Balance refactor (#432) and validation_info cleanup (#434) by @hyeok9855.
• Discrete mask caching (#465), score-dict accumulation (#469), and validate_environment flag (#466) by @younik.
• Box environment simplification (#480), log-prob bugfix (#484), simplified uniform module (#485) by @josephdviviano.
• L1 distance fix (mean→sum, #488), MLP noisy-layers bound tightening (#482), OUTPUT_DIR constant extraction (#459) by @Copilot.
• Dummy/exit actions for graph building (#442, #450), device handling tweaks (#437, #439) by @josephdviviano.
• Assertion moved out of hot path into tests (#438, @ali-m07).
• Logging uniformization (#462, #464, #490), print removal (#462) by @younik.
• Coverage reporting and Codecov CI integration (#452–#458, @josephdviviano + @Copilot).
• Pre-commit as separate CI job, Python version bump (#474, @younik).
• Tutorial/test n_hidden_layers bump to match refactored MLP semantics (#486).
• Heatmap and plotting helpers (#477 @younik, #463 @josephdviviano).

Contributors

• @josephdviviano — broadest footprint: compile/benchmark infra, RTB loss, loss optimization, box env, device handling, coverage, docs.
• @younik — logging, mask caching, CI.
• @hyeok9855 — conditional GFlowNet redesign, DB refactor, container tests, discrete env fixes.
• @chirayuharyan — replay buffer accumulation.
• @ali-m07 — assertion refactor.
• @Copilot — automated fixes (L1 distance, MLP bounds, codecov config, OUTPUT_DIR).

Full Changelog: v2.3.1...v2.4.0

v2.3.1

What's Changed

• Bugfixes for device handling by @josephdviviano in #426

Full Changelog: v2.3.0...v2.3.1

v2.3.0

What's Changed

• Multinode training: timing profiles, seeding, distributed asynchronous training (including selective policy averaging) by @josephdviviano, @chirayuharyan, @younik in #260, #335, #418, #341, #395, #401, #403, #411, #417, #420
• Move to PolicyMixin to factorize Sampler and Estimator logic by @josephdviviano in #413 and #410
• Diffusion Sampling by @hyeok9855 and @josephdviviano in #419
• Simplification and enhancement of node classes in graph sampling by @younik in #386, #387
• Expanded off policy sampling methods by @josephdviviano in #388
• Efficient TerminatingStateBuffer by @hyeok9855 in #392
• hypergrid refactor by @josephdviviano in #402
• Misc fixes by @hyeok9855, @josephdviviano in #391, #397, #399, #398

Full Changelog: v2.2.2...v2.3.0

v2.2.2

What's Changed

• Fix conditional GFlowNet training by @saleml in #385

Full Changelog: v2.2.1...v2.2.2

v2.2.1

What's Changed

• [HOTFIX] Fix mode discovery metrics by @saleml in #384

Full Changelog: v2.2.0...v2.2.1

v2.2.0

High Level

• Added Generative Augmented Flow Networks example (https://arxiv.org/abs/2210.03308), which specifies intermediate rewards with intrinsic motivation to help with the exploration problem in sparse reward environments.
• Extended graph functionality (e.g., add nodes as an action).
• More efficient autoregressive GFN training.

What's Changed

• Add GAFN for hypergrid with sparse reward by @hyeok9855 in #375
• Add graph example with add node action by @younik in #378
• Misc efficiency improvements by @hyeok9855 in #376
• Simplify GraphActionGNN by @younik in #382
• Don't allow removal of nodes with edges by @younik in #381
• minor change to allow for pb to be None when the gflownet's DAG is a tree by @josephdviviano in #371

Full Changelog: v2.1.1...v2.2.0

v2.1.1

What's Changed

• Add custom mRNA codon design environment by @ayalaajil in #350
• Fix broken conditional training script by @saleml in #372

New Contributors

• @ayalaajil made their first contribution in #350

Full Changelog: v2.1.0...v2.1.1

v2.1.0

What's Changed

• Documentation updates by @hyeok9855 in #352
• Rename GFNModule to Estimator. (removing the notion of GFNModules from the library entirely) by @hyeok9855 in #353
• consistent dtype handling library-wide by @josephdviviano in #358
• typing consistency fixes library-wide
• misc minor fixes

Full Changelog: v2.0.1...v2.1.0

v2.0.1

What's Changed

• Multiple improvements to replay buffers.
• Support for conditional GFNs.
• Support for graph-based states (using torch_geometric).
• Major improvements supporting reproducible experiments in distributed settings.
• Various quality of life improvements, small features, optimizations, and refactorings.
• Complete type safety - library-wide adherence to pyright, while dropping torchtyping.
• Improved documentation.
• Addition of many new environments in gfn/gym.
• Addition of new tutorials and examples demonstrating advanced usage of torchgfn.
• Reproduction of DAG-GFlowNet (Bayesian Structure learning, Deleu et al., 2022).
• Local search sampler (Local Search GFlowNets, Kim et al., 2024).

New Contributors

• @inelgnu made their first contribution in #192
• @younik made their first contribution in #202
• @hyeok9855 made their first contribution in #203
• @alexandrelarouche made their first contribution in #232
• @Idriss-Malek made their first contribution in #236
• @emirceyani made their first contribution in #240
• @alip67 made their first contribution in #210

Full Changelog: v1.2.1...v2.0.1