Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation
- URL: http://arxiv.org/abs/2501.14856v2
- Date: Wed, 12 Feb 2025 10:36:26 GMT
- Title: Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation
- Authors: Anish Abhijit Diwan, Julen Urain, Jens Kober, Jan Peters,
- Abstract summary: This paper introduces a new imitation learning framework based on energy-based generative models.
We learn complex, physics-dependent, robot motion policies through state-only expert motion trajectories.
Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques.
- Score: 17.73467861849673
- License:
- Abstract: This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert's motion data distribution and learns smooth, and well-defined representations of the data distribution's energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via reinforcement learning. We also present a strategy to gradually switch between the learnt energy functions, ensuring that the learnt rewards are always well-defined in the manifold of policy-generated samples. We evaluate our algorithm on complex humanoid tasks such as locomotion and martial arts and compare it with state-only adversarial imitation learning algorithms like Adversarial Motion Priors (AMP). Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques and produces results comparable to AMP in several quantitative metrics across multiple imitation settings.
Related papers
- Revisiting Energy Based Models as Policies: Ranking Noise Contrastive
Estimation and Interpolating Energy Models [18.949193683555237]
In this work, we revisit the choice of energy-based models (EBM) as a policy class.
We develop a training objective and algorithm for energy models which combines several key ingredients.
We show that the Implicit Behavior Cloning (IBC) objective is actually biased even at the population level.
arXiv Detail & Related papers (2023-09-11T20:13:47Z) - CoopInit: Initializing Generative Adversarial Networks via Cooperative
Learning [50.90384817689249]
CoopInit is a cooperative learning-based strategy that can quickly learn a good starting point for GANs.
We demonstrate the effectiveness of the proposed approach on image generation and one-sided unpaired image-to-image translation tasks.
arXiv Detail & Related papers (2023-03-21T07:49:32Z) - Weighted Maximum Entropy Inverse Reinforcement Learning [22.269565708490468]
We study inverse reinforcement learning (IRL) and imitation learning (IM)
We propose a new way to improve the learning process by adding the maximum weight function to the entropy framework.
Our framework and algorithms allow to learn both a reward (or policy) function and the structure of the entropy terms added to the Markov Decision Processes.
arXiv Detail & Related papers (2022-08-20T06:02:07Z) - Assessing Evolutionary Terrain Generation Methods for Curriculum
Reinforcement Learning [3.1971316044104254]
We compare popular noise-based terrain generators to two indirect encodings, CPPN and GAN.
We assess the impact of a range of representation-agnostic MAP-Elites feature descriptors that compute metrics directly from the generated terrain meshes.
Results describe key differences between the generators that inform their use in curriculum learning, and present a range of useful feature descriptors for uptake by the community.
arXiv Detail & Related papers (2022-03-29T01:26:15Z) - Energy-Efficient and Federated Meta-Learning via Projected Stochastic
Gradient Ascent [79.58680275615752]
We propose an energy-efficient federated meta-learning framework.
We assume each task is owned by a separate agent, so a limited number of tasks is used to train a meta-model.
arXiv Detail & Related papers (2021-05-31T08:15:44Z) - Composable Learning with Sparse Kernel Representations [110.19179439773578]
We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space.
We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function.
We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment.
arXiv Detail & Related papers (2021-03-26T13:58:23Z) - Shared Prior Learning of Energy-Based Models for Image Reconstruction [69.72364451042922]
We propose a novel learning-based framework for image reconstruction particularly designed for training without ground truth data.
In the absence of ground truth data, we change the loss functional to a patch-based Wasserstein functional.
In shared prior learning, both aforementioned optimal control problems are optimized simultaneously with shared learned parameters of the regularizer.
arXiv Detail & Related papers (2020-11-12T17:56:05Z) - Learning Discrete Energy-based Models via Auxiliary-variable Local
Exploration [130.89746032163106]
We propose ALOE, a new algorithm for learning conditional and unconditional EBMs for discrete structured data.
We show that the energy function and sampler can be trained efficiently via a new variational form of power iteration.
We present an energy model guided fuzzer for software testing that achieves comparable performance to well engineered fuzzing engines like libfuzzer.
arXiv Detail & Related papers (2020-11-10T19:31:29Z) - Strictly Batch Imitation Learning by Energy-based Distribution Matching [104.33286163090179]
Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment.
One solution is simply to retrofit existing algorithms for apprenticeship learning to work in the offline setting.
But such an approach leans heavily on off-policy evaluation or offline model estimation, and can be indirect and inefficient.
We argue that a good solution should be able to explicitly parameterize a policy, implicitly learn from rollout dynamics, and operate in an entirely offline fashion.
arXiv Detail & Related papers (2020-06-25T03:27:59Z) - Energy-Based Imitation Learning [29.55675131809474]
We tackle a common scenario in imitation learning (IL) where agents try to recover the optimal policy from expert demonstrations.
Inspired by recent progress in energy-based model (EBM), in this paper we propose a simplified IL framework named Energy-Based Imitation Learning (EBIL)
EBIL combines the idea of both EBM and occupancy measure matching, and via theoretic analysis we reveal that EBIL and Max-Entropy IRL (MaxEnt IRL) approaches are two sides of the same coin.
arXiv Detail & Related papers (2020-04-20T15:49:35Z) - Contextual Policy Transfer in Reinforcement Learning Domains via Deep
Mixtures-of-Experts [24.489002406693128]
We introduce a novel mixture-of-experts formulation for learning state-dependent beliefs over source task dynamics.
We show how this model can be incorporated into standard policy reuse frameworks.
arXiv Detail & Related papers (2020-02-29T07:58:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.