REVIEW 16 cited by
Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining inputs, together with representations of time horizons and other computable functions of historic and desired future data. UDRL learns to interpret these input observations as commands, mapping them to actions (or action probabilities) through SL on past (possibly accidental) experience. UDRL generalizes to achieve high rewards or other goals, through input commands such as: get lots of reward within at most so much time! A separate paper [63] on first experiments with UDRL shows that even a pilot version of UDRL can outperform traditional baseline algorithms on certain challenging RL problems. We also also conceptually simplify an approach [60] for teaching a robot to imitate humans. First videotape humans imitating the robot's current behaviors, then let the robot learn through SL to map the videos (as input commands) to these behaviors, then let it generalize and imitate videos of humans executing previously unknown behavior. This Imitate-Imitator concept may actually explain why biological evolution has resulted in parents who imitate the babbling of their babies.
Forward citations
Cited by 16 Pith papers
-
Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
Success conditioning exactly maximizes linearized policy improvement under a chi-squared divergence trust region whose radius is action-influence, with relative improvement, policy change, and action-influence exactly...
-
Single-pass Adaptive Image Tokenization for Minimum Program Search
KARL conditions a tokenizer on a target reconstruction loss and learns halting probabilities that produce an adaptive token count in a single forward pass.
-
Freeform Preference Learning for Robotic Manipulation
Language-conditioned multi-axis human preferences yield denser rewards and steerable robot policies that outperform sparse and binary-preference baselines by 38 points on long-horizon manipulation.
-
Freeform Preference Learning for Robotic Manipulation
Freeform Preference Learning trains language-conditioned multi-axis reward models from human pairwise preferences to produce steerable and compositional robot policies that outperform sparse and binary-preference base...
-
Freeform Preference Learning for Robotic Manipulation
FPL trains a language-conditioned reward model from per-axis human preferences and a reward-conditioned policy, reporting 38-point average success gains over sparse-reward and binary-preference baselines on six manipu...
-
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
FlowR2A learns reward-conditioned action distributions via flow-matching decoder to unify dense reward supervision with dynamic proposal generation for multimodal driving planning.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer achieves state-of-the-art results in offline goal-conditioned RL by replacing return-to-go with a state-conditioned Q-estimator and introducing a gated hybrid attention-mamba backbone for content-adaptive histor...
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markov...
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
Behavioral Exploration: Learning to Explore via In-Context Adaptation
A coverage-conditioned behavioral cloning policy adapts in-context to its own history, making robots explore new expert-like behaviors online without online reinforcement learning.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
Is Conditional Generative Modeling all you need for Decision-Making?
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.
-
LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
LEMUR jointly learns a separate reward model for each teacher's preferences and uses them to train a population of multi-objective policies, beating baselines that merge feedback into one reward.
-
GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration
A goal-agnostic curiosity reward is claimed to make active geo-localization agents generalize better to unseen targets and environments than distance-based rewards.
-
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
BYOL-γ uses self-predictive representations to approximate successor representations, improving zero-shot combinatorial generalization in goal-conditioned behavioral cloning.
-
Reinforcement Learning: From Algorithms To Foundation Models
A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.
Discussion (0). Sign in to comment.