CLAIRE-Labo / no-representation-no-trustLinks
Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (Moalla et al. 2024). Uses TorchRL and provides extensive tools for studying representation dynamics in policy optimization.
☆26Updated 6 months ago
Alternatives and similar repositories for no-representation-no-trust
Users that are interested in no-representation-no-trust are comparing it to the libraries listed below
Sorting:
- Learning diverse options through the Laplacian representation.☆23Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆70Updated last year
- Unified Implementations of Offline Reinforcement Learning Algorithms☆80Updated last month
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆48Updated last week
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆101Updated last year
- Conservative Q learning in Jax☆54Updated 2 years ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆57Updated last year
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆16Updated 2 years ago
- Extreme Q-Learning: Max Entropy RL without Entropy☆88Updated 2 years ago
- Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023☆46Updated 2 weeks ago
- PyTorch Package For Quasimetric Learning☆42Updated 7 months ago
- ☆45Updated 2 years ago
- ☆31Updated 4 years ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- ☆79Updated 2 months ago
- Code for the paper "Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference"☆42Updated 10 months ago
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- ☆24Updated 11 months ago
- Action Value Gradient Algorithm☆21Updated 2 weeks ago
- VC-FB and MC-FB algorithms from "Zero-Shot Reinforcement Learning from Low Quality Data" (NeurIPS 2024)☆16Updated 4 months ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆84Updated 6 months ago
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆101Updated last year
- ☆15Updated 2 years ago
- Codebase for "Uni[MASK]: Unified Inference in Sequential Decision Problems"☆55Updated 11 months ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated last month
- Building blocks for productive research☆55Updated 4 months ago
- ☆47Updated 2 years ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆167Updated 2 months ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆73Updated 9 months ago
- General Modules for JAX☆66Updated 2 months ago