Dhruv Sreenivas's repositories
byol-offline
Bootstrap your own latent (BYOL) methods in offline reinforcement learning
dqn_zoo
DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.
jax_sandbox
JAX messaround
OfflineRL-Kit
An elegant PyTorch offline reinforcement learning library for researchers.
lightATAC-rlhf
A lightweight reimplementation of Adversarially Trained Actor Critic
acme
A library of reinforcement learning components and agents.
IsaacGymEnvs
Isaac Gym Reinforcement Learning Environments
amp_milo
Model based offline imitation learning on AMP tasks.
v-d4rl
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
IQ-Learn
(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation
amp_extensions
Extension of AMP framework (https://github.com/xbpeng/DeepMimic) to include gym environment. Also, adapted code from MILO (https://github.com/jdchang1/milo) to test on AMP framework.
gym-simplifiedtetris
🟥 Simplified Tetris environments compliant with OpenAI Gym's API
dm_control
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
DeepMimic
Motion imitation with deep reinforcement learning.
pillbox
Contains implementation of AdVIL, AdRIL, and DAeQuIL algorithms from the ICML '21 Paper Of Moments and Matching.
rl-trained-agents
A collection of pre-trained RL agents using Stable Baselines3
TD3_BC
Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL
pytorch_sac
PyTorch implementation of Soft Actor-Critic (SAC)
pytorch-a2c-trpo-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
homework_fall2020
Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)
dots-and-boxes
Testing various AI methods for the game Dots & Boxes
sqil-atari
Implementation of SQIL for Atari games
dril
Disagreement-Regularized Imitation Learning