dojeon-ai / Atari-PB
Official repository for "Investigating Pre-Training Objectives for Generalization in Visual Reinforcement Learning" (ICML 2024)
☆10Updated 7 months ago
Alternatives and similar repositories for Atari-PB:
Users that are interested in Atari-PB are comparing it to the libraries listed below
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆42Updated 2 weeks ago
- ☆81Updated 2 months ago
- ☆25Updated last year
- Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).☆42Updated last year
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆80Updated 4 months ago
- Synthetic Experience Replay☆91Updated 11 months ago
- ☆11Updated last year
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆73Updated 11 months ago
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆68Updated last year
- ☆23Updated 6 months ago
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆100Updated 11 months ago
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆28Updated 8 months ago
- Foundation Policies with Hilbert Representations (ICML 2024)☆83Updated last year
- Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)☆56Updated 6 months ago
- Official codebase for GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning.☆19Updated 5 months ago
- ☆61Updated 5 months ago
- ☆43Updated 5 months ago
- ☆13Updated 4 months ago
- Learning diverse options through the Laplacian representation.☆23Updated last year
- Transformer-based World Models☆80Updated 2 years ago
- ☆15Updated last year
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- A benchmark for offline goal-conditioned RL and offline RL☆157Updated 3 weeks ago
- ☆31Updated last year
- Unified Implementations of Offline Reinforcement Learning Algorithms☆56Updated this week
- official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning☆92Updated 8 months ago
- Official code for TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations☆30Updated 6 months ago
- Listwise Reward Estimation for Offline Preference-based Reinforcement Learning (ICML 2024)☆14Updated 10 months ago
- ☆21Updated last year
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.☆23Updated last year