FelipeNuti / diffusion-relative-rewards
Codebase for Extracting Reward Functions from Diffusion Models
☆11Updated 9 months ago
Related projects: ⓘ
- [ICML'2023] "AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners"☆45Updated 11 months ago
- ☆43Updated 3 months ago
- [NeurIPS 2023] Efficient Diffusion Policy☆74Updated 10 months ago
- Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).☆36Updated 7 months ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆71Updated 10 months ago
- ☆20Updated 11 months ago
- Official implementation for: Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning ICLR'24☆20Updated 3 weeks ago
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆52Updated 3 months ago
- ☆24Updated last year
- Masked World Models for Visual Control☆114Updated last year
- ☆69Updated 2 years ago
- Code for NeurIPS 2023 paper "Active Vision Reinforcement Learning with Limited Visual Observability"☆48Updated 6 months ago
- Transformer-based World Models☆66Updated last year
- ☆17Updated 6 months ago
- Skill-based Model-based Reinforcement Learning (CoRL 2022)☆50Updated last year
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆81Updated 10 months ago
- Coarse-to-fine Q-Network☆26Updated last month
- ☆51Updated last year
- ☆71Updated last year
- ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models☆40Updated 5 months ago
- ☆34Updated last year
- Codebase of NeurIPS 2022 paper ''Planning for Sample Efficient Imitation Learning''☆34Updated last year
- ☆38Updated 10 months ago
- ☆48Updated 6 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆21Updated 10 months ago
- This is the repo of "RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization"☆90Updated last week
- Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.☆71Updated 4 months ago
- ☆21Updated last month
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆131Updated 11 months ago
- Code for "TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning"☆19Updated 4 months ago