Demo-JEPA enables one-shot cross-embodiment imitation by mapping visual demonstrations to shared latent future trajectories that serve as subgoals for the target agent's own forward dynamics planning.
hub
Behavioral Cloning from Observation
30 Pith papers cite this work. Polarity classification is still indexing.
30
Pith papers citing it
abstract
Humans often learn how to perform tasks via imitation: they observe others perform a task, and then very quickly infer the appropriate actions to take based on their observations. While extending this paradigm to autonomous agents is a well-studied problem in general, there are two particular aspects that have largely been overlooked: (1) that the learning is done from observation only (i.e., without explicit action information), and (2) that the learning is typically done very quickly. In this work, we propose a two-phase, autonomous imitation learning technique called behavioral cloning from observation (BCO), that aims to provide improved performance with respect to both of these aspects. First, we allow the agent to acquire experience in a self-supervised fashion. This experience is used to develop a model which is then utilized to learn a particular task by observing an expert perform that task without the knowledge of the specific actions taken. We experimentally compare BCO to imitation learning methods, including the state-of-the-art, generative adversarial imitation learning (GAIL) technique, and we show comparable task performance in several different simulation domains while exhibiting increased learning speed after expert trajectories become available.
hub tools
citation-role summary
background 2
method 1
other 1
citation-polarity summary
representative citing papers
SeqRejectron constructs a stopping rule with a small set of validator policies to achieve horizon-free sample complexity for selective imitation learning under arbitrary dynamics shifts.
A new meta-training algorithm, ELO, combines a failure-aware resume buffer with progressive expert supervision; its best learned optimizer, ELO-Celo2, outperforms AdamW on ImageNet and GPT-2 and matches Muon on language modeling.
AnyBody distills a privileged teacher tracker into a latent unit-sphere representation and uses a masked transformer to drive humanoid control from arbitrary keypoint subsets.
Deep RL with action decomposition and reward shifting learns a symbolic multi-parameter policy for (1+(λ,λ))-GA on OneMax that outperforms baselines across problem sizes.
DIBS decouples task policy learning via RL from evolution function learning via behavioral cloning to achieve more stable training and better generalization than prior RL and meta-RL methods for inductive generalization from specifications.
FA-OPD co-trains a flow-matching teacher and MLP student via adversarial dual on-policy distillation, improving robustness over baselines on six robot benchmarks with noisy or limited demonstrations.
Proposes Cost-Aware Adaptive Conformal Inference framework providing dual statistical guarantees on long-run violation frequency and cumulative violation cost for runtime assurance in dynamic environments.
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
HITL-D combines diffusion policies with human input for shared robotic control, reducing required joystick axes and improving speed and workload in manipulation tasks per a 12-participant study.
TimeRewarder derives step-wise progress rewards from frame-wise temporal distances in passive videos and uses them to guide RL, achieving high success rates on Meta-World tasks with fewer interactions than prior methods or hand-designed rewards.
DAWM introduces a modular diffusion world model with an inverse dynamics model to produce complete synthetic transitions that improve conservative offline RL algorithms like TD3BC and IQL on D4RL tasks.
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
SemBid injects LLM-encoded Task, History, and Strategy semantics as tokens into offline bidding trajectories and uses self-attention to outperform numerical-only baselines in performance, constraint satisfaction, and robustness.
A framework decouples failure data for value estimation and success data for policy learning in offline RL to reduce collisions in robot navigation while maintaining success rates.
PTMT is a lightweight framework that automates parameter tuning for memory tiering via hybrid offline database building and online customized reinforcement learning, delivering 14-30% gains over defaults and 32% over prior art on four systems.
Veo-3 video predictions enable approximate task-level robot trajectories in zero-shot settings but require hierarchical integration with low-level VLA policies for reliable manipulation performance.
CORE extracts visual goal prototypes from terminal embeddings in action-free demonstrations to condition robot policies, reporting success rate gains of up to 17 percentage points on manipulation benchmarks.
ReGIL retrieves segments from a single demonstration to compute local temporal-alignment rewards and guide policy training, achieving >75% success on three real-robot tasks with <1 hour of online data.
A simulation framework generates diverse reach-to-grasp demonstrations to train imitation learning policies for biosignals-free prosthetic grasping, achieving over 90% success in sim-to-real transfer.
SPADE combines sketch-guided path planning with diffusion-augmented imitation learning to achieve better generalization and lower error with fewer parameters than prior methods.
PACTS jointly model action trajectories and predicate belief trajectories in a single generative policy, enabling zero-shot skill composition via symbolic planning without retraining.
COOPO is a cyclic offline-online RL algorithm that repeatedly anchors the policy to a dataset via KL-regularized updates then fine-tunes online, claiming better sample efficiency and monotonic improvement under coverage assumptions.
citing papers explorer
-
Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
SeqRejectron constructs a stopping rule with a small set of validator policies to achieve horizon-free sample complexity for selective imitation learning under arbitrary dynamics shifts.