REVIEW 5 cited by
Learning to Act without Actions
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
read the original abstract
Pre-training large models on vast amounts of web data has proven to be an effective approach for obtaining powerful, general models in domains such as language and vision. However, this paradigm has not yet taken hold in reinforcement learning. This is because videos, the most abundant form of embodied behavioral data on the web, lack the action labels required by existing methods for imitating behavior from demonstrations. We introduce Latent Action Policies (LAPO), a method for recovering latent action information, and thereby latent-action policies, world models, and inverse dynamics models, purely from videos. LAPO is the first method able to recover the structure of the true action space just from observed dynamics, even in challenging procedurally-generated environments. LAPO enables training latent-action policies that can be rapidly fine-tuned into expert-level policies, either offline using a small action-labeled dataset, or online with rewards. LAPO takes a first step towards pre-training powerful, generalist policies and world models on the vast amounts of videos readily available on the web.
Forward citations
Cited by 5 Pith papers
-
DWM: Separating World Effects from Actions in Latent World Models
A training-time 'world head' that is action-invariant, plus an orthogonality constraint, improves CEM planning in latent world models when environments have persistent action-independent dynamics (average +13.1 pp on ...
-
Causally Debiased Latent Action Model for Embodied Action Conditioned World Models
Three lightweight LAM fine-tuning objectives (foreground-weighted reconstruction, primitive contrastive learning, zero-transition calibration) debias latent actions and yield stronger, cheaper robot-action following i...
-
Factored Latent Action World Models
FLAM splits a scene into separate factors, each with its own latent action, and reports better video prediction and downstream policy learning than monolithic latent-action models.
-
Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation
Editing a frozen RL policy's latent activations at inference time, using a collision world model, cuts collisions by about 90% on a curated set of hard multirotor scenarios and on real Crazyflies.
-
Latent Action Learning Requires Supervision in the Presence of Distractors
Latent action models need at least a small amount of action supervision to learn useful actions when observations contain distractors, as shown on the Distracting Control Suite.
Discussion (0). Continue with ORCID to comment.